Home New Trending Search
About Privacy Terms
#
#Issue
Posts tagged #Issue on Bluesky
Henry White
Henry White
@wonterland.bsky.social
16 hours ago
Video thumbnail

Thought I would give you an update on the messy, chalk-covered wet bed sleeper, which seems to have gotten worse after all the winter rain.

#train #trainspotting #swr #southwesternrailway #class444 #desiro #networkrail #railway #sleeper #wetbed #wet #bed #issue #problem #messy #chalk #itsback

2 0 0 0
2rZiKKbOU3nTafniR2qMMSE0gwZ
2rZiKKbOU3nTafniR2qMMSE0gwZ
@2rzikkbou3ntafnir2qmmse0gwz.activitypub.awakari.com.ap.brid.gy
1 day ago
Adaptive Security Reliability Meta Monitoring Framework for Cybersecurity Detection Systems **DOI :****10.17577/IJERTV15IS030073** Download Full-Text PDF Cite this Publication Prof. T B Dharmaraj, Mathan Raj A, M. Hemalatha, Arunajayan A P, Iniyavan M, Madhu Priya V R, 2026, Adaptive Security Reliability Meta Monitoring Framework for Cybersecurity Detection Systems, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume 15, Issue 03 , March – 2026 * **Open Access** * Article Download / Views: 0 * **Authors :** Prof. T B Dharmaraj, Mathan Raj A, M. Hemalatha, Arunajayan A P, Iniyavan M, Madhu Priya V R * **Paper ID :** IJERTV15IS030073 * **Volume & Issue : ** Volume 15, Issue 03 , March – 2026 * **Published (First Online):** 14-03-2026 * **ISSN (Online) :** 2278-0181 * **Publisher Name :** IJERT * **License:** This work is licensed under a Creative Commons Attribution 4.0 International License __ PDF Version View __ Text Only Version #### Adaptive Security Reliability Meta Monitoring Framework for Cybersecurity Detection Systems Prof. T B Dharmaraj Head of the Department (Mentor) Department of Information Technology PPG Institute of Technology, Tamil Nadu, India Mathan Raj A Department of Information Technology PPG Institute of Technology, Tamil Nadu, India M. Hemalatha Assistant Professor (Mentor) Department of Information Technology PPG Institute of Technology, Tamil Nadu, India Arunajayan A P Department of Information Technology PPG Institute of Technology, Tamil Nadu, India Iniyavan M Department of Information Technology PPG Institute of Technology, Tamil Nadu, India Madhu Priya V R Department of Information Technology PPG Institute of Technology, Tamil Nadu, India Abstract – Cybersecurity detection systems such as intrusion detection systems and endpoint detection platforms may lose effectiveness over time due to evolving threats and system drift. This paper proposes the Adaptive Security Reliability Meta Monitoring Framework (ASRM), a monitoring layer that continuously evaluates detection reliability using drift analysis, entropy monitoring, blind spot probability modeling, and adver- sarial simulation techniques. The framework generates a Security Reliability Score (SRS) that quantifies the operational reliability of enterprise security monitoring systems. Experimental evalu- ation demonstrates that the proposed framework can identify reliability degradation and improve cybersecurity resilience. Index Terms – Cybersecurity, Detection Reliability, Drift Anal- ysis, Blind Spot Detection, Security Monitoring, Machine Learn- ing 1. INTRODUCTION Cybersecurity infrastructures depend on detection systems such as intrusion detection systems, endpoint detection plat- forms, and security information and event management plat- forms to identify malicious activities. However, the effective- ness of these systems may degrade over time due to evolving attack techniques, configuration changes, and incomplete de- tection coverage. Most existing security tools focus primarily on threat de- tection rather than evaluating the reliability of the detection infrastructure itself. As a result, monitoring blind spots may remain undetected, increasing the risk of successful cyber attacks. To address this problem, this paper proposes the Adaptive Security Reliability Meta Monitoring Framework (ASRM), a monitoring layer that continuously evaluates the reliability of cybersecurity detection systems using statistical analysis and adversarial simulation techniques. 2. RELATED WORK Intrusion detection systems are widely used to detect mali- cious activities in network environments. Traditional signature-based detection approaches rely on predefined attack signa- tures and often fail to detect unknown threats. Machine learning techniques have been introduced to im- prove anomaly detection in cybersecurity environments. How- ever, most existing research focuses on detecting attacks rather than evaluating the reliability of detection systems. Security Information and Event Management platforms pro- vide centralized monitoring by aggregating logs from multiple security tools. Despite their usefulness, SIEM systems typi- cally lack mechanisms to measure detection reliability. The proposed ASRM framework addresses this gap by introducing a reliability monitoring layer that evaluates de- tection effectiveness using statistical analysis and adversarial simulations. 3. SYSTEM ARCHITECTURE The ASRM framework operates as a meta monitoring layer integrated with existing cybersecurity detection infrastructure. The framework collects telemetry data from intrusion detection systems, endpoint detection platforms, firewalls, authentication systems, and SIEM platforms. The collected logs are normalized and processed through multiple reliability evaluation modules including drift analysis, entropy monitoring, blind spot detection, and adversarial simu- lation. The outputs of these modules are combined to compute a Security Reliability Score. 4. SYSTEM DATA PREPARATION Security telemetry data is collected from multiple sources including IDS, EDR, firewalls, authentication logs, and SIEM platforms. The collected data is normalized to ensure consis- tent representation across different sources. Data preprocessing includes removal of duplicate records, handling missing values, and classification of events based on severity levels. The processed dataset is stored in a centralized monitoring database for reliability evaluation. Fig. 1. Adaptive Security Reliability Meta Monitoring Framework Architec- ture 5. RELIABILITY METRICS The ASRM framework evaluates detection effectiveness using statistical reliability metrics. 1. Detection Drift Score Measures deviations between current detection patterns and historical baseline behavior. 2. Coverage Score Represents the percentage of simulated threats successfully detected by security monitoring systems. 3. Entropy Score Measures the diversity and randomness of detection alerts. 4. Adversarial Simulation Score Evaluates detection capability using simulated attack sce- narios. 5. Security Reliability Score The overall reliability of the detection infrastructure is represented by the Security Reliability Score. SRS = Wd · D + Wc · C + We · E + Wa · A (1) where * D = Detection Drift Score * C = Coverage Score * E = Entropy Score * A = Adversarial Simulation Score * Wd, Wc, We, Wa = weighting factors The weighting factors satisfy: Wd + Wc + We + Wa = 1 (2) 6. SYSTEM IMPLEMENTATION The ASRM framework was implemented using Python for statistical analysis and reliability computation. Log processing was performed using the Pandas and NumPy libraries, while entropy and drift calculations were implemented using SciPy. The monitoring dashboard was developed using a lightweight web interface for visualization of reliability scores. 7. EXPERIMENTAL EVALUATION The proposed framework was evaluated using publicly available cybersecurity datasets including CICIDS2017 and UNSW-NB15. A. Evaluation Metrics * Detection Drift Score * Coverage Score * Entropy Score * Adversarial Detection Rate TABLE I Reliability Evaluation Results Metric Value Detection Drift Score 84 Coverage Score 88 Entropy Score 79 Adversarial Detection Rate 85 Security Reliability Score (SRS) 84 8. CONCLUSION This paper presented the Adaptive Security Reliability Monitor framework for evaluating the reliability of enterprise cybersecurity monitoring systems. The proposed approach introduces reliability-centric monitoring using drift analysis, entropy monitoring, blind spot detection, and adversarial sim- ulation. The framework generates aSecurity Reliability Score that provides a measurable indicator of monitoring effectiveness. By identifying reliability degradation and monitoring blind spots, the ASRM framework improves cybersecurity resilience and situational awareness. FUTURE WORK Future work will focus on integrating real-time machine learning models to improve detection reliability evaluation. Additional adversarial simulation scenarios will be developed to test monitoring resilience in large-scale enterprise and cloud environments. ACKNOWLEDGMENT The authors thank Prof T B Dharmaraj and M. Hemalatha for their guidance and support during the development of this research work. REFERENCES 1. NIST, Guide to Intrusion Detection and Prevention Systems, Special Publication 800-94, 2007. 2. C. Kruegel, F. Valeur, and G. Vigna, Intrusion Detection and Correla- tion: Challenges and Solutions. Springer, 2005. 3. R. Sommer and V. Paxson, Outside the closed world: On using machine learning for network intrusion detection, IEEE Symposium on Security and Privacy, 2010. 4. S. Axelsson, The base-rate fallacy and its implications for intrusion detection, ACM CCS, 1999. 5. OWASP Foundation, OWASP Top Ten Web Application Security Risks, 2021. 6. T. Lunt, A survey of intrusion detection techniques, Computers and Security, 1993. 7. W. Lee and S. Stolfo, Data mining approaches for intrusion detection, USENIX Security Symposium, 1998. 8. M. Roesch, Snort: Lightweight intrusion detection for networks, USENIX LISA Conference, 1999. 9. D. Denning, An intrusion-detection model, IEEE Transactions on Software Engineering, 1987. 10. M. Tavallaee et al., A detailed analysis of the KDD CUP 99 data set, IEEE CISDA, 2009. 11. I. Sharafaldin et al., Toward generating a new intrusion detection dataset, ICISSP, 2018. 12. NSA, Defensive Cyber Operations Guidance, NSA Cybersecurity Di- rectorate, 2022. 13. M. Ring, D. Wunderlich, D. Scheuring, D. Landes, and A. Hotho, A survey of network-based intrusion detection data sets, Computers & Security, vol. 86, pp. 147167, 2019. 14. I. Sharafaldin, A. Habibi Lashkari, and A. Ghorbani, Toward generating a new intrusion detection dataset and intrusion traffic characterization, in Proc. International Conference on Information Systems Security and Privacy, 2018. 15. N. Moustafa and J. Slay, UNSW-NB15: A comprehensive data set for network intrusion detection systems, in Military Communications and Information Systems Conference, 2015. 16. A. Javaid, Q. Niyaz, W. Sun, and M. Alam, A deep learning approach for network intrusion detection system, in Proc. IEEE International Conference on Computing, Networking and Communications, 2016. 17. S. Berman, A. Buczak, J. Chavis, and C. Corbett, A survey of deep learning methods for cyber security, Information, vol. 10, no. 4, 2019. 18. A. Khraisat, I. Gondal, P. Vamplew, and J. Kamruzzaman, Survey of intrusion detection systems: Techniques, datasets, and challenges, Cybersecurity, vol. 2, no. 1, 2019. Fig. 2. Data Flow of the Adaptive Security Reliability Meta Monitoring Framework ______________

Adaptive Security Reliability Meta Monitoring Framework for Cybersecurity Detection Systems View Abstract & download full text of Adaptive Security Reliability Meta Monitoring Framework for Cyb...

#Volume #15, #Issue #03 #(March #2026)

Origin | Interest | Match

0 0 0 0
2rZiKKbOU3nTafniR2qMMSE0gwZ
2rZiKKbOU3nTafniR2qMMSE0gwZ
@2rzikkbou3ntafnir2qmmse0gwz.activitypub.awakari.com.ap.brid.gy
1 day ago
Adaptive Security Reliability Meta Monitoring Framework for Cybersecurity Detection Systems **DOI :****10.17577/IJERTV15IS030073** Download Full-Text PDF Cite this Publication Prof. T B Dharmaraj, Mathan Raj A, M. Hemalatha, Arunajayan A P, Iniyavan M, Madhu Priya V R, 2026, Adaptive Security Reliability Meta Monitoring Framework for Cybersecurity Detection Systems, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume 15, Issue 03 , March – 2026 * **Open Access** * Article Download / Views: 0 * **Authors :** Prof. T B Dharmaraj, Mathan Raj A, M. Hemalatha, Arunajayan A P, Iniyavan M, Madhu Priya V R * **Paper ID :** IJERTV15IS030073 * **Volume & Issue : ** Volume 15, Issue 03 , March – 2026 * **Published (First Online):** 14-03-2026 * **ISSN (Online) :** 2278-0181 * **Publisher Name :** IJERT * **License:** This work is licensed under a Creative Commons Attribution 4.0 International License __ PDF Version View __ Text Only Version #### Adaptive Security Reliability Meta Monitoring Framework for Cybersecurity Detection Systems Prof. T B Dharmaraj Head of the Department (Mentor) Department of Information Technology PPG Institute of Technology, Tamil Nadu, India Mathan Raj A Department of Information Technology PPG Institute of Technology, Tamil Nadu, India M. Hemalatha Assistant Professor (Mentor) Department of Information Technology PPG Institute of Technology, Tamil Nadu, India Arunajayan A P Department of Information Technology PPG Institute of Technology, Tamil Nadu, India Iniyavan M Department of Information Technology PPG Institute of Technology, Tamil Nadu, India Madhu Priya V R Department of Information Technology PPG Institute of Technology, Tamil Nadu, India Abstract – Cybersecurity detection systems such as intrusion detection systems and endpoint detection platforms may lose effectiveness over time due to evolving threats and system drift. This paper proposes the Adaptive Security Reliability Meta Monitoring Framework (ASRM), a monitoring layer that continuously evaluates detection reliability using drift analysis, entropy monitoring, blind spot probability modeling, and adver- sarial simulation techniques. The framework generates a Security Reliability Score (SRS) that quantifies the operational reliability of enterprise security monitoring systems. Experimental evalu- ation demonstrates that the proposed framework can identify reliability degradation and improve cybersecurity resilience. Index Terms – Cybersecurity, Detection Reliability, Drift Anal- ysis, Blind Spot Detection, Security Monitoring, Machine Learn- ing 1. INTRODUCTION Cybersecurity infrastructures depend on detection systems such as intrusion detection systems, endpoint detection plat- forms, and security information and event management plat- forms to identify malicious activities. However, the effective- ness of these systems may degrade over time due to evolving attack techniques, configuration changes, and incomplete de- tection coverage. Most existing security tools focus primarily on threat de- tection rather than evaluating the reliability of the detection infrastructure itself. As a result, monitoring blind spots may remain undetected, increasing the risk of successful cyber attacks. To address this problem, this paper proposes the Adaptive Security Reliability Meta Monitoring Framework (ASRM), a monitoring layer that continuously evaluates the reliability of cybersecurity detection systems using statistical analysis and adversarial simulation techniques. 2. RELATED WORK Intrusion detection systems are widely used to detect mali- cious activities in network environments. Traditional signature-based detection approaches rely on predefined attack signa- tures and often fail to detect unknown threats. Machine learning techniques have been introduced to im- prove anomaly detection in cybersecurity environments. How- ever, most existing research focuses on detecting attacks rather than evaluating the reliability of detection systems. Security Information and Event Management platforms pro- vide centralized monitoring by aggregating logs from multiple security tools. Despite their usefulness, SIEM systems typi- cally lack mechanisms to measure detection reliability. The proposed ASRM framework addresses this gap by introducing a reliability monitoring layer that evaluates de- tection effectiveness using statistical analysis and adversarial simulations. 3. SYSTEM ARCHITECTURE The ASRM framework operates as a meta monitoring layer integrated with existing cybersecurity detection infrastructure. The framework collects telemetry data from intrusion detection systems, endpoint detection platforms, firewalls, authentication systems, and SIEM platforms. The collected logs are normalized and processed through multiple reliability evaluation modules including drift analysis, entropy monitoring, blind spot detection, and adversarial simu- lation. The outputs of these modules are combined to compute a Security Reliability Score. 4. SYSTEM DATA PREPARATION Security telemetry data is collected from multiple sources including IDS, EDR, firewalls, authentication logs, and SIEM platforms. The collected data is normalized to ensure consis- tent representation across different sources. Data preprocessing includes removal of duplicate records, handling missing values, and classification of events based on severity levels. The processed dataset is stored in a centralized monitoring database for reliability evaluation. Fig. 1. Adaptive Security Reliability Meta Monitoring Framework Architec- ture 5. RELIABILITY METRICS The ASRM framework evaluates detection effectiveness using statistical reliability metrics. 1. Detection Drift Score Measures deviations between current detection patterns and historical baseline behavior. 2. Coverage Score Represents the percentage of simulated threats successfully detected by security monitoring systems. 3. Entropy Score Measures the diversity and randomness of detection alerts. 4. Adversarial Simulation Score Evaluates detection capability using simulated attack sce- narios. 5. Security Reliability Score The overall reliability of the detection infrastructure is represented by the Security Reliability Score. SRS = Wd · D + Wc · C + We · E + Wa · A (1) where * D = Detection Drift Score * C = Coverage Score * E = Entropy Score * A = Adversarial Simulation Score * Wd, Wc, We, Wa = weighting factors The weighting factors satisfy: Wd + Wc + We + Wa = 1 (2) 6. SYSTEM IMPLEMENTATION The ASRM framework was implemented using Python for statistical analysis and reliability computation. Log processing was performed using the Pandas and NumPy libraries, while entropy and drift calculations were implemented using SciPy. The monitoring dashboard was developed using a lightweight web interface for visualization of reliability scores. 7. EXPERIMENTAL EVALUATION The proposed framework was evaluated using publicly available cybersecurity datasets including CICIDS2017 and UNSW-NB15. A. Evaluation Metrics * Detection Drift Score * Coverage Score * Entropy Score * Adversarial Detection Rate TABLE I Reliability Evaluation Results Metric Value Detection Drift Score 84 Coverage Score 88 Entropy Score 79 Adversarial Detection Rate 85 Security Reliability Score (SRS) 84 8. CONCLUSION This paper presented the Adaptive Security Reliability Monitor framework for evaluating the reliability of enterprise cybersecurity monitoring systems. The proposed approach introduces reliability-centric monitoring using drift analysis, entropy monitoring, blind spot detection, and adversarial sim- ulation. The framework generates aSecurity Reliability Score that provides a measurable indicator of monitoring effectiveness. By identifying reliability degradation and monitoring blind spots, the ASRM framework improves cybersecurity resilience and situational awareness. FUTURE WORK Future work will focus on integrating real-time machine learning models to improve detection reliability evaluation. Additional adversarial simulation scenarios will be developed to test monitoring resilience in large-scale enterprise and cloud environments. ACKNOWLEDGMENT The authors thank Prof T B Dharmaraj and M. Hemalatha for their guidance and support during the development of this research work. REFERENCES 1. NIST, Guide to Intrusion Detection and Prevention Systems, Special Publication 800-94, 2007. 2. C. Kruegel, F. Valeur, and G. Vigna, Intrusion Detection and Correla- tion: Challenges and Solutions. Springer, 2005. 3. R. Sommer and V. Paxson, Outside the closed world: On using machine learning for network intrusion detection, IEEE Symposium on Security and Privacy, 2010. 4. S. Axelsson, The base-rate fallacy and its implications for intrusion detection, ACM CCS, 1999. 5. OWASP Foundation, OWASP Top Ten Web Application Security Risks, 2021. 6. T. Lunt, A survey of intrusion detection techniques, Computers and Security, 1993. 7. W. Lee and S. Stolfo, Data mining approaches for intrusion detection, USENIX Security Symposium, 1998. 8. M. Roesch, Snort: Lightweight intrusion detection for networks, USENIX LISA Conference, 1999. 9. D. Denning, An intrusion-detection model, IEEE Transactions on Software Engineering, 1987. 10. M. Tavallaee et al., A detailed analysis of the KDD CUP 99 data set, IEEE CISDA, 2009. 11. I. Sharafaldin et al., Toward generating a new intrusion detection dataset, ICISSP, 2018. 12. NSA, Defensive Cyber Operations Guidance, NSA Cybersecurity Di- rectorate, 2022. 13. M. Ring, D. Wunderlich, D. Scheuring, D. Landes, and A. Hotho, A survey of network-based intrusion detection data sets, Computers & Security, vol. 86, pp. 147167, 2019. 14. I. Sharafaldin, A. Habibi Lashkari, and A. Ghorbani, Toward generating a new intrusion detection dataset and intrusion traffic characterization, in Proc. International Conference on Information Systems Security and Privacy, 2018. 15. N. Moustafa and J. Slay, UNSW-NB15: A comprehensive data set for network intrusion detection systems, in Military Communications and Information Systems Conference, 2015. 16. A. Javaid, Q. Niyaz, W. Sun, and M. Alam, A deep learning approach for network intrusion detection system, in Proc. IEEE International Conference on Computing, Networking and Communications, 2016. 17. S. Berman, A. Buczak, J. Chavis, and C. Corbett, A survey of deep learning methods for cyber security, Information, vol. 10, no. 4, 2019. 18. A. Khraisat, I. Gondal, P. Vamplew, and J. Kamruzzaman, Survey of intrusion detection systems: Techniques, datasets, and challenges, Cybersecurity, vol. 2, no. 1, 2019. Fig. 2. Data Flow of the Adaptive Security Reliability Meta Monitoring Framework ______________

Adaptive Security Reliability Meta Monitoring Framework for Cybersecurity Detection Systems View Abstract & download full text of Adaptive Security Reliability Meta Monitoring Framework for Cyb...

#Volume #15, #Issue #03 #(March #2026)

Origin | Interest | Match

0 0 0 0
MongoDB
MongoDB
@mongodb.activitypub.awakari.com.ap.brid.gy
1 day ago
Digital Department Logbook & Academic Management System **DOI :****10.17577/IJERTV15IS030350** Download Full-Text PDF Cite this Publication Jeevanantham G, Amrutha S, Aswini R, Ramya S, Visakh P J, 6 Yusvaanth A S, 2026, Digital Department Logbook & Academic Management System, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume 15, Issue 03 , March – 2026 * **Open Access** * Article Download / Views: 0 * **Authors :** Jeevanantham G, Amrutha S, Aswini R, Ramya S, Visakh P J, 6 Yusvaanth A S * **Paper ID :** IJERTV15IS030350 * **Volume & Issue : ** Volume 15, Issue 03 , March – 2026 * **Published (First Online):** 14-03-2026 * **ISSN (Online) :** 2278-0181 * **Publisher Name :** IJERT * **License:** This work is licensed under a Creative Commons Attribution 4.0 International License __ PDF Version View __ Text Only Version #### Digital Department Logbook & Academic Management System (1)Jeevanantham G, (2) Amrutha S, (3) Aswini R, (4) Ramya S, (5) Visakh P J, (6) Yusvaanth A S (1)Assistant Professor (Senior Grade), (12345)Department of Computer Science and Engineering (12345) Nehru Institute of Engineering and Technology Coimbatore -641105 Abstract : Educational institutions handle a huge amount of academic data on a regular basis. These include students’ attendance, internal marks, assignments, evaluation of seminars, and regular academic activities. Most of these academic activities are handled manually, either by maintaining a paper log or by using spreadsheet software. Handling academic records manually often causes problems like computational mistakes, redundancy of data, problems in retrieving data, and lack of transparency for students. Faculty members often spend more time managing records instead of devoting their valuable time to teaching and academic improvements. To overcome these problems, this project aims to implement a Digital Department Logbook & Academic Management System (DDLAMS). DDLAMS is a centralized academic management system that helps manage academic records efficiently within the academic department. Faculty members can easily manage students’ attendance, internal marks, assignments, and regular academic activities through an online interface. Students can also access their records. The system is built using the MERN stack, which includes MongoDB, Express.js, React.js, and Node.js. These technologies enable the system to offer a user interface, security, and effective management of data. Role-Based Access Control (RBAC) is used to offer different access levels for administrators, faculty members, and students. JWT and bcrypt are security techniques used for authenticating and encrypting user data. The implementation of this system ensures transparency, reduces administrative burden, and ensures effective management of academic records. It contributes to the digital transformation of educational institutions by replacing traditional methods with an effective and secure web-based system. Keywords : Academic Management System, Digital Logbook, MERN Stack, Attendance Management, Student Record Management, Role-Based Access Control 1. INTRODUCTION : Educational institutions play an important role in maintaining and managing the academic records of the students. Academic records include student attendance, internal marks, assignment marks, seminar marks, and daily class activities. Managing academic records is important for monitoring the performance of the students and for easy management of academic institutions. For many academic departments, records are managed using traditional methods such as maintaining registers and using spreadsheet files. Although this has been followed for many years, it has many disadvantages. For example, manual records may lead to many human errors, and performing many calculations for attendance and marks may be time- consuming. Managing many registers may not be useful for maintaining and accessing old academic records. Another important factor is the lack of transparency for the students. For example, the attendance and internal marks are not available for the students unless they are announced. This may lead to many confusions and misconceptions about the performance of the students. However, with the advancement of web technologies and digital systems, educational institutions can now use modern technologies to efficiently manage academic records. A digital academic management system can efficiently manage all the data of the departments, as well as automate various processes such as calculating attendance and evaluating marks. A Digital Department Logbook & Academic Management System (DDLAMS) can be used as a solution for the academic departments of educational institutions. The digital logbook will allow the faculty members to efficiently manage the academic records of the departments through a web-based platform. Students can also view their academic records through a digital platform. 2. PROBLEM STATEMENT : Academic departments deal with a lot of information regarding student activities and performance. Still, the traditional methods are used for maintaining these records. There are certain issues with the traditional method of maintaining academic records. The faculty members have to maintain the records of student attendance and marks manually in registers. The calculation of attendance percentages and internal marks for every student is time-consuming and increases the chances of errors. There is also a problem of storage. The academic records are not centrally stored; instead, the information is stored in different registers or files. This creates a problem when the information is required for some purpose. For instance, during academic audits or reviews in the academic departments, the collection of information from the registers or files takes a lot of time. Students are also facing certain issues as the information is not provided to them in a transparent manner. The student does not have the accessibility to the academic records. Therefore, there is a need for a digital solution that can assist in the automation of academic records. 3. OBJECTIVES OF THE STUDY : The main objective of the Digital Department Logbook & Academic Management System is to create an efficient digital platform for the management of academic information. The specific objectives are as follows: * Digitize department logbook records * Reduce paperwork and administration * Provide central storage of academic information * Improve accuracy in attendance and mark calculations * Increase transparency for students * Provide secure access through authentication * Simplify academic reporting and information retrieval By achieving these objectives, it is possible to significantly enhance the efficiency of departmental academic management. 4. LITERATURE SURVEY : Several research works and systems have been developed to enhance academic records management in learning institutions. The Student Information System (SIS) is widely used for storing student information, including personal information, course registration, and results. However, these systems have been mainly used for administrative purposes. Learning Management Systems (LMS) like Moodle and Google Classroom have also been widely used for academic records management. These systems enable learning institutions to conduct online learning activities. They allow tutors to upload assignments, track student performance, and monitor their progress. However, these systems have mainly been used for online learning. Some learning institutions have also used automated attendance management systems that make use of RFID cards, biometric identification, or QR codes. However, these systems have mainly been used for attendance management. Several research works have also been conducted on academic records management, suggesting that integrating different academic functions into one digital platform can enhance efficiency in academic records management, thus reducing data duplication. The Digital Department Logbook & Academic Management System is a platform that combines different academic functions, including attendance managemnt, academic evaluation, and departmental records management, into one platform. 5. EXISTING SYSTEM : In the existing system, the academic records are maintained manually using a paper register or a spreadsheet file. The faculty members record the attendances during each class session and calculate the percentage of attendances manually. Internal assessment marks and assignment scores are also maintained manually. This calculation is often repeated many times, which may cause errors. Another drawback in the existing system is that the data is not stored centrally. Each faculty member may be maintaining the data separately, which may be a problem when the data is required. 6. PROPOSED SYSTEM : The proposed Digital Department Logbook & Academic Management System seeks to address the limitations of the current manual system. The proposed system allows faculty members to record student attendance, update marks, and maintain academic records electronically using a web-based platform. The data collected will be stored in a centralized database. Students can use the proposed system to view their attendance percentage, internal marks, and academic performance. The proposed system ensures that the student has read-only privileges. This proposed system is more efficient and ensures the accuracy of academic record management. 7. SYSTEM ARCHITECTURE : The Digital Department Logbook & Academic Management System (DDLAMS) is developed based on a three-tier architecture model. In this architecture model, there are three layers in which the system is implemented: the Frontend Layer, the Backend Layer, and the Database Layer. Each layer has its own functions, which communicate with other layers for an efficient system. Frontend Layer: The frontend layer is responsible for providing an interface for users. In DDLAMS, the frontend is implemented by using React.js, which is an open-source JavaScript library for building modern web applications. React.js is widely used for developing robust web applications. The frontend is considered the bridge between users and the system. In DDLAMS, different users have different interfaces for different functionalities. Faculty members have different interfaces for different functionalities, such as attendance, internal marks, uploading assignment marks, and daily academic log maintenance. Similarly, different interfaces are provided for different users, such as for students and administrators. Faculty members can maintain attendance records, internal marks, upload their assignment marks, and maintain their daily academic log through the frontend provided by DDLAMS. Similarly, students can log in to the DDLAMS system and view their attendance records, internal marks, and academic log maintained by their faculty members. Additionally, React.js helps in updating the user interface dynamically without reloading the entire page. This improves the performance of the application. Backend Layer : The backend layer is responsible for handling the business logic of the application, which includes processing the data requests received from the frontend layer. In this project, Node.js and Express.js have been used for developing the backend layer. Node.js Node.js is a runtime environment that helps in running JavaScript on the server side. Node.js is known for its high performance, which enables it to handle multiple requests at any given time. Express.js Express.js is a lightweight web development framework that is built on Node.js. Express.js is known for its simplicity in developing web applications. The backend layer has many important tasks to perform, including processing user requests, validating data, authenticating users, and communicating with the database. For example, when a user records their attendance on the frontend layer, the request is sent to the backend server for processing. The request is processed, and the required information is retrieved from the database. The processed information is then sent back to the frontend layer. The second important task that is performed by the backend layer is related to user authentication and authorization. The verification of users identity is performed by this system before allowing them to access the features provided by the application. Database Layer : The database layer is responsible for storing all the academic information that is used by the system. In this project, MongoDB is used as the database management system. MongoDB is a NoSQL database management system that stores information in document form. In this project, academic information is stored in document form, which is very flexible for storing large amounts of information in an efficient manner. The academic information stored in the database includes information about students, staff members, attendance records, marks for assignments, evaluation of seminars, daily academic information, etc. Each type of academic information is stored separately in the database. In addition, MongoDB also supports the efficient retrieval of information, which is very beneficial for displaying academic information to users of the system. The records of all the activities performed in each department of the university can be stored securely in the central database, which can be retrieved when needed. 8. SYSTEM DESIGN : System design is another significant step in the development of the Digital Department Logbook & Academic Management System (DDLAMS). The main aim of the system design is to create an efficient system so that the Digital Department Logbook & Academic Management System can run efficiently and meet the needs of the users. The main aim of the system design is to create a user- friendly interface and a database system for the users. The Digital Department Logbook & Academic Management System is designed for multiple users, including the administrator, faculty members, and students. The users have different roles and permissions to use the system. To allow the users to use the system efficiently, the Digital Department Logbook & Academic Management System provides a separate dashboard for each type of user. The administrator dashboard allows the administrator to manage the users of the system, add or remove users from the system, and manage the settings of the system. The administrator also ensures that the academic records are maintained efficiently within the system. The faculty dashboard has been designed in such a manner that teachers can easily carry out their academic tasks. Using this dashboard, teachers can easily record attendance, internal marks, assignment marks, and daily academic logs. For this purpose, simple forms and input fields have been provided, ensuring accurate input of information. The student dashboard has been designed for the purpose of providing students with accurate information regarding their academic performance. Using this dashboard, students can easily keep track of their attendance percentages, internal marks, assignment marks, and seminar marks. This will help create transparency and provide accurate information to the students. While designing this system, it was ensured that there was a smooth flow of information between the frontend, backend, and database layers. Information provided by teachers is stored in the database and then presented to the students using the user interface. 9. METHODOLOGY : The methodology for the development of the Digital Department Logbook & Academic Management System is a structured approach to ensure the system meets the requirements of the users and runs effectively. The methodology for the development of the system involves a number of steps. Requirement Analysis The first step in the development of the system is the requirement analysis. In this step, the problems associated with the existing system are analyzed.Faculty members find it difficult to maintain registers and calculate attendance or internal marks. Similarly, students do not have easy access to their academic records. Based on the problems of the existing system, the requirements of the digital academic management system are analyzed. System Design After the analysis of the requirements of the digital academic management system, the next step is the system design. This phase of the system design focuses on the architecture of the system. The architecture of the system is designed to meet the requirements of the users. The design of the system focuses on the database of the system. Development This is the stage where the system will be implemented using the various technologies of the MERN stack. The front-end of the system will be built using React.js, while the back-end will be built using Node.js and Express.js. The data storage of the academic information will be handled by MongoDB. Testing This stage is used to test the functions of the system to ensure they are working properly. This is the stage where errors and bugs are found and corrected. The testing of the system will be used to ensure the system will be able to record attendance, store academic information, and control user access. Deployment This is the stage where the system will be deployed to the department. The faculty members of the department will be able to access the system through a web browser. This is the stage where the system will be ready for the real world. 10. SYSTEM MODULES : The Digital Department Logbook & Academic Management System has various modules to enable each user to perform a particular function effectively. This helps in the organization of the system. Staff Module : The Staff Module is for the faculty members of the college. Faculty members are responsible for the management of the academic records. This module helps the teachers to maintain the student records effectively. Functions of the Staff Module: Recording the attendance of the students Recording the internal assessment marks of the students Uploading the marks of the assignments Evaluating the seminar presentations of the students Maintaining the class logs This module helps the teachers to maintain the academic records of the students. The teachers do not have to maintain the records in a physical logbook. Student Module : This module allows students to access their academic records using a login ID. The students have read access to the information, meaning they can only read the information but cannot edit it. Students can read: Attendance percentage Internal assessment marks Assignment results Seminar evaluation scores This module increases transparency for the students. 11. DATABASE DESIGN : The role of database design in the efficient storage and management of academic data cannot be overstated. For this project, MongoDB is used as the database management system. MongoDB MongoDB is a database management system that belongs to the category of NoSQL databases. This means that the data is stored in a document format. Database Design There are a number of collections in the database, each used to store different data. Users Collection In this collection, the login information of the administrator, faculty, and students is stored. Students Collection In this collection, the information of the students, including student ID, name, and department, is stored. Attendance Collection In this collection, the daily attendance information of the students is stored. Assignments Collection This collection holds information about the assignments and the marks for each student. Internal Marks Collection This collection holds information about the internal assessment data for each student. Seminar Evaluations Collection This collection holds the marks for the student seminar evaluations. 1. ER DIAGRAM EXPLANATION : Entity Relationship Diagram The Entity Relationship (ER) Diagram shows the structure of the database and the relationships among various entities of the system. The major entities of the system include Student, Staff, Attendance, Assignments, Internal Marks, and Seminar Evaluations. Student The Student entity includes various attributes like student ID, name, department, etc. Every student has his/her attendance, assignment marks, and internal marks. Staff Staff members are the faculty of the college. They handle the attendance of the students, the assignment marks of the students, etc. Attendance This entity stores the attendance of the students on a daily basis. This entity is related to the Student entity through the student ID. Assignments This entity stores the details of the assignments given to the students along with the marks obtained by the students for the assignments. Every assignment record is related to a particular student. Internal Marks This entity stores the marks obtained by the students for various subjects. Seminar Evaluations This entity stores the marks obtained by the students for the presentation of the seminars. 2. USE CASE DIAGRAM : The Use Case Diagram shows how different users interact with each other. It helps to understand the application of the application and how each user plays their role. There are three main users of this application. They are as follows: Administrator Faculty Member Student The role of the Administrator includes managing users, setting system settings, and monitoring academic data. The Faculty Member can perform tasks such as recording attendance, updating internal marks, managing assignments, and conducting seminars. The role of the Student includes logging into the application to access their attendance, internal marks, and academic progress. The use case diagram shows how each user can interact with each other. 3. IMPLEMENTATION : The Digital Department Logbook & Academic Management System is based on the MERN stack technology. The MERN stack technology offers a new framework for creating efficient and scalable web applications. The frontend of the Digital Department Logbook & Academic Management System is based on React.js, which offers an interactive and efficient user interface for the system. React components are used to create various dashboards and forms, enabling users to interact with the system easily. The backend of the Digital Department Logbook & Academic Management System is based on Node.js and Express.js, which offer efficient and scalable backend operations for the system. These operations include processing user requests, authenticating users, and interacting with the database. The system is based on the MongoDB database, which stores all the academic records, such as student data, attendance, assignment marks, and seminar evaluations. The system offers efficient and secure authentication options for users. JSON Web Tokens (JWT) are used to verify the users during the login session. Passwords are encrypted using bcrypt and stored in the database. All the above-mentioned technologies have been used to create a reliable and efficient system for managing the department’s academic records. 4. RESULTS AND DISCUSSION : After the implementation of the Digital Department Logbook & Academic Management System, some changes have been observed in the academic record management process. For instance, the faculty members can now record the attendance and marks of the students digitally without the need for maintaining a record. The data will be automatically recorded in the database, thus eliminating the chances of errors. Students can now view the academic performance using the student dashboard. This increases the level of transparency for the students, as they can now keep track of the performance throughout the semester.Using the database, the academic record management has been made easier for the administrators. 5. ADVANTAGES OF THE SYSTEM : * It minimizes manual records * It increases accuracy * It offers a centralized data management system * It increases transparency for students * It saves time for faculty members 6. LIMITATIONS : Drawbacks of using this system: * It requires an internet connection * It may require technical support during installation * Users must be trained to use the system 7. FUTURE ENHANCEMENTS : Possible improvements that can be added to this system in the future include support for a mobile application, integration of biometric devices with attendance, AI-based analysis of performances, and notification for students. 8. REFERENCE : 1. Mokhtar, M. N., Suhaini, S. A., Abdullah, F. H., et al. (2024). A survey of anaesthetic training logbook management among postgraduate students. BMC Medical Education, 24(867). 2. Shafiq, D. A., Marjani, M., Habeeb, R. A., & Asirvatham, D. (2025). Digital Footprints of Academic Success: An Empirical Analysis of Moodle Logs and Traditional Factors for Student Performance. Education Sciences, 15(3), 304. 3. Mustafa, R., & Mustafa, K. (2025). Student Records Management System using IoT. International Journal of Computational and Experimental Science and Engineering. 4. Lontaan, R. J., & Sinadia, A. R. (2024). Design and Development of a Web-Based School Information System. CogITo Smart Journal, 10(2), 593606. 5. Makkaraka, A. M. R. B., Iskandar, A., & Wang, Y. (2024). Design of Web-Based Student Academic Information System. Ceddi Journal of Education, 3(2), 915. 6. Sanchez, L., Penarreta, J., & Soria Poma, X. (2024). Learning Management Systems for Higher Education: A Comparative Study. Discover Education Journal. 7. Kerimbayev, N., Adamova, K., & Shadiev, R. (2025). Intelligent Educational Technologies in Individual Learning: A Systematic Literature Review. Smart Learning Environments Journal. 8. OECD. (2023). OECD Digital Education Outlook 2023: Towards an Effective Digital Education Ecosystem. OECD Publishing. 9. Purnomo, E. N., Imron, A., Wiyono, B. B., & Sobri, A. Y. (2024). Transformation of Digital-Based School Culture and Virtual Learning Environment Integration. Cogent Education Journal. 10. Oxyandi, M., Panduragan, S. L., Said, F. M., & Saputra, M. A. (2023). Use of Electronic Logbook Based on Mobile Learning in Clinical Learning among Students. American Journal of Medical Science and Innovation. 9. CONCLUSION: The Digital Class Log Book System offers an efficient and modern alternative for academic record management for academic institutions. The system replaces the conventional logbook with a digital version that allows lecturers to record daily activities for their classes, attendance, assignments, and internal assessment records in an organized manner. With the implementation of the system, the academic records of the students can be managed securely by the lecturers and the academic institutions. Lecturers can manage the subject records of the students, while the students can view their academic records through the dashboard provided by the system. ______________

Digital Department Logbook & Academic Management System View Abstract & download full text of Digital Department Logbook & Academic Management System Download Full-Text PDF Cite this Pu...

#Volume #15, #Issue #03 #(March #2026)

Origin | Interest | Match

0 0 0 0
MongoDB
MongoDB
@mongodb.activitypub.awakari.com.ap.brid.gy
1 day ago
Digital Department Logbook & Academic Management System **DOI :****10.17577/IJERTV15IS030350** Download Full-Text PDF Cite this Publication Jeevanantham G, Amrutha S, Aswini R, Ramya S, Visakh P J, 6 Yusvaanth A S, 2026, Digital Department Logbook & Academic Management System, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume 15, Issue 03 , March – 2026 * **Open Access** * Article Download / Views: 0 * **Authors :** Jeevanantham G, Amrutha S, Aswini R, Ramya S, Visakh P J, 6 Yusvaanth A S * **Paper ID :** IJERTV15IS030350 * **Volume & Issue : ** Volume 15, Issue 03 , March – 2026 * **Published (First Online):** 14-03-2026 * **ISSN (Online) :** 2278-0181 * **Publisher Name :** IJERT * **License:** This work is licensed under a Creative Commons Attribution 4.0 International License __ PDF Version View __ Text Only Version #### Digital Department Logbook & Academic Management System (1)Jeevanantham G, (2) Amrutha S, (3) Aswini R, (4) Ramya S, (5) Visakh P J, (6) Yusvaanth A S (1)Assistant Professor (Senior Grade), (12345)Department of Computer Science and Engineering (12345) Nehru Institute of Engineering and Technology Coimbatore -641105 Abstract : Educational institutions handle a huge amount of academic data on a regular basis. These include students’ attendance, internal marks, assignments, evaluation of seminars, and regular academic activities. Most of these academic activities are handled manually, either by maintaining a paper log or by using spreadsheet software. Handling academic records manually often causes problems like computational mistakes, redundancy of data, problems in retrieving data, and lack of transparency for students. Faculty members often spend more time managing records instead of devoting their valuable time to teaching and academic improvements. To overcome these problems, this project aims to implement a Digital Department Logbook & Academic Management System (DDLAMS). DDLAMS is a centralized academic management system that helps manage academic records efficiently within the academic department. Faculty members can easily manage students’ attendance, internal marks, assignments, and regular academic activities through an online interface. Students can also access their records. The system is built using the MERN stack, which includes MongoDB, Express.js, React.js, and Node.js. These technologies enable the system to offer a user interface, security, and effective management of data. Role-Based Access Control (RBAC) is used to offer different access levels for administrators, faculty members, and students. JWT and bcrypt are security techniques used for authenticating and encrypting user data. The implementation of this system ensures transparency, reduces administrative burden, and ensures effective management of academic records. It contributes to the digital transformation of educational institutions by replacing traditional methods with an effective and secure web-based system. Keywords : Academic Management System, Digital Logbook, MERN Stack, Attendance Management, Student Record Management, Role-Based Access Control 1. INTRODUCTION : Educational institutions play an important role in maintaining and managing the academic records of the students. Academic records include student attendance, internal marks, assignment marks, seminar marks, and daily class activities. Managing academic records is important for monitoring the performance of the students and for easy management of academic institutions. For many academic departments, records are managed using traditional methods such as maintaining registers and using spreadsheet files. Although this has been followed for many years, it has many disadvantages. For example, manual records may lead to many human errors, and performing many calculations for attendance and marks may be time- consuming. Managing many registers may not be useful for maintaining and accessing old academic records. Another important factor is the lack of transparency for the students. For example, the attendance and internal marks are not available for the students unless they are announced. This may lead to many confusions and misconceptions about the performance of the students. However, with the advancement of web technologies and digital systems, educational institutions can now use modern technologies to efficiently manage academic records. A digital academic management system can efficiently manage all the data of the departments, as well as automate various processes such as calculating attendance and evaluating marks. A Digital Department Logbook & Academic Management System (DDLAMS) can be used as a solution for the academic departments of educational institutions. The digital logbook will allow the faculty members to efficiently manage the academic records of the departments through a web-based platform. Students can also view their academic records through a digital platform. 2. PROBLEM STATEMENT : Academic departments deal with a lot of information regarding student activities and performance. Still, the traditional methods are used for maintaining these records. There are certain issues with the traditional method of maintaining academic records. The faculty members have to maintain the records of student attendance and marks manually in registers. The calculation of attendance percentages and internal marks for every student is time-consuming and increases the chances of errors. There is also a problem of storage. The academic records are not centrally stored; instead, the information is stored in different registers or files. This creates a problem when the information is required for some purpose. For instance, during academic audits or reviews in the academic departments, the collection of information from the registers or files takes a lot of time. Students are also facing certain issues as the information is not provided to them in a transparent manner. The student does not have the accessibility to the academic records. Therefore, there is a need for a digital solution that can assist in the automation of academic records. 3. OBJECTIVES OF THE STUDY : The main objective of the Digital Department Logbook & Academic Management System is to create an efficient digital platform for the management of academic information. The specific objectives are as follows: * Digitize department logbook records * Reduce paperwork and administration * Provide central storage of academic information * Improve accuracy in attendance and mark calculations * Increase transparency for students * Provide secure access through authentication * Simplify academic reporting and information retrieval By achieving these objectives, it is possible to significantly enhance the efficiency of departmental academic management. 4. LITERATURE SURVEY : Several research works and systems have been developed to enhance academic records management in learning institutions. The Student Information System (SIS) is widely used for storing student information, including personal information, course registration, and results. However, these systems have been mainly used for administrative purposes. Learning Management Systems (LMS) like Moodle and Google Classroom have also been widely used for academic records management. These systems enable learning institutions to conduct online learning activities. They allow tutors to upload assignments, track student performance, and monitor their progress. However, these systems have mainly been used for online learning. Some learning institutions have also used automated attendance management systems that make use of RFID cards, biometric identification, or QR codes. However, these systems have mainly been used for attendance management. Several research works have also been conducted on academic records management, suggesting that integrating different academic functions into one digital platform can enhance efficiency in academic records management, thus reducing data duplication. The Digital Department Logbook & Academic Management System is a platform that combines different academic functions, including attendance managemnt, academic evaluation, and departmental records management, into one platform. 5. EXISTING SYSTEM : In the existing system, the academic records are maintained manually using a paper register or a spreadsheet file. The faculty members record the attendances during each class session and calculate the percentage of attendances manually. Internal assessment marks and assignment scores are also maintained manually. This calculation is often repeated many times, which may cause errors. Another drawback in the existing system is that the data is not stored centrally. Each faculty member may be maintaining the data separately, which may be a problem when the data is required. 6. PROPOSED SYSTEM : The proposed Digital Department Logbook & Academic Management System seeks to address the limitations of the current manual system. The proposed system allows faculty members to record student attendance, update marks, and maintain academic records electronically using a web-based platform. The data collected will be stored in a centralized database. Students can use the proposed system to view their attendance percentage, internal marks, and academic performance. The proposed system ensures that the student has read-only privileges. This proposed system is more efficient and ensures the accuracy of academic record management. 7. SYSTEM ARCHITECTURE : The Digital Department Logbook & Academic Management System (DDLAMS) is developed based on a three-tier architecture model. In this architecture model, there are three layers in which the system is implemented: the Frontend Layer, the Backend Layer, and the Database Layer. Each layer has its own functions, which communicate with other layers for an efficient system. Frontend Layer: The frontend layer is responsible for providing an interface for users. In DDLAMS, the frontend is implemented by using React.js, which is an open-source JavaScript library for building modern web applications. React.js is widely used for developing robust web applications. The frontend is considered the bridge between users and the system. In DDLAMS, different users have different interfaces for different functionalities. Faculty members have different interfaces for different functionalities, such as attendance, internal marks, uploading assignment marks, and daily academic log maintenance. Similarly, different interfaces are provided for different users, such as for students and administrators. Faculty members can maintain attendance records, internal marks, upload their assignment marks, and maintain their daily academic log through the frontend provided by DDLAMS. Similarly, students can log in to the DDLAMS system and view their attendance records, internal marks, and academic log maintained by their faculty members. Additionally, React.js helps in updating the user interface dynamically without reloading the entire page. This improves the performance of the application. Backend Layer : The backend layer is responsible for handling the business logic of the application, which includes processing the data requests received from the frontend layer. In this project, Node.js and Express.js have been used for developing the backend layer. Node.js Node.js is a runtime environment that helps in running JavaScript on the server side. Node.js is known for its high performance, which enables it to handle multiple requests at any given time. Express.js Express.js is a lightweight web development framework that is built on Node.js. Express.js is known for its simplicity in developing web applications. The backend layer has many important tasks to perform, including processing user requests, validating data, authenticating users, and communicating with the database. For example, when a user records their attendance on the frontend layer, the request is sent to the backend server for processing. The request is processed, and the required information is retrieved from the database. The processed information is then sent back to the frontend layer. The second important task that is performed by the backend layer is related to user authentication and authorization. The verification of users identity is performed by this system before allowing them to access the features provided by the application. Database Layer : The database layer is responsible for storing all the academic information that is used by the system. In this project, MongoDB is used as the database management system. MongoDB is a NoSQL database management system that stores information in document form. In this project, academic information is stored in document form, which is very flexible for storing large amounts of information in an efficient manner. The academic information stored in the database includes information about students, staff members, attendance records, marks for assignments, evaluation of seminars, daily academic information, etc. Each type of academic information is stored separately in the database. In addition, MongoDB also supports the efficient retrieval of information, which is very beneficial for displaying academic information to users of the system. The records of all the activities performed in each department of the university can be stored securely in the central database, which can be retrieved when needed. 8. SYSTEM DESIGN : System design is another significant step in the development of the Digital Department Logbook & Academic Management System (DDLAMS). The main aim of the system design is to create an efficient system so that the Digital Department Logbook & Academic Management System can run efficiently and meet the needs of the users. The main aim of the system design is to create a user- friendly interface and a database system for the users. The Digital Department Logbook & Academic Management System is designed for multiple users, including the administrator, faculty members, and students. The users have different roles and permissions to use the system. To allow the users to use the system efficiently, the Digital Department Logbook & Academic Management System provides a separate dashboard for each type of user. The administrator dashboard allows the administrator to manage the users of the system, add or remove users from the system, and manage the settings of the system. The administrator also ensures that the academic records are maintained efficiently within the system. The faculty dashboard has been designed in such a manner that teachers can easily carry out their academic tasks. Using this dashboard, teachers can easily record attendance, internal marks, assignment marks, and daily academic logs. For this purpose, simple forms and input fields have been provided, ensuring accurate input of information. The student dashboard has been designed for the purpose of providing students with accurate information regarding their academic performance. Using this dashboard, students can easily keep track of their attendance percentages, internal marks, assignment marks, and seminar marks. This will help create transparency and provide accurate information to the students. While designing this system, it was ensured that there was a smooth flow of information between the frontend, backend, and database layers. Information provided by teachers is stored in the database and then presented to the students using the user interface. 9. METHODOLOGY : The methodology for the development of the Digital Department Logbook & Academic Management System is a structured approach to ensure the system meets the requirements of the users and runs effectively. The methodology for the development of the system involves a number of steps. Requirement Analysis The first step in the development of the system is the requirement analysis. In this step, the problems associated with the existing system are analyzed.Faculty members find it difficult to maintain registers and calculate attendance or internal marks. Similarly, students do not have easy access to their academic records. Based on the problems of the existing system, the requirements of the digital academic management system are analyzed. System Design After the analysis of the requirements of the digital academic management system, the next step is the system design. This phase of the system design focuses on the architecture of the system. The architecture of the system is designed to meet the requirements of the users. The design of the system focuses on the database of the system. Development This is the stage where the system will be implemented using the various technologies of the MERN stack. The front-end of the system will be built using React.js, while the back-end will be built using Node.js and Express.js. The data storage of the academic information will be handled by MongoDB. Testing This stage is used to test the functions of the system to ensure they are working properly. This is the stage where errors and bugs are found and corrected. The testing of the system will be used to ensure the system will be able to record attendance, store academic information, and control user access. Deployment This is the stage where the system will be deployed to the department. The faculty members of the department will be able to access the system through a web browser. This is the stage where the system will be ready for the real world. 10. SYSTEM MODULES : The Digital Department Logbook & Academic Management System has various modules to enable each user to perform a particular function effectively. This helps in the organization of the system. Staff Module : The Staff Module is for the faculty members of the college. Faculty members are responsible for the management of the academic records. This module helps the teachers to maintain the student records effectively. Functions of the Staff Module: Recording the attendance of the students Recording the internal assessment marks of the students Uploading the marks of the assignments Evaluating the seminar presentations of the students Maintaining the class logs This module helps the teachers to maintain the academic records of the students. The teachers do not have to maintain the records in a physical logbook. Student Module : This module allows students to access their academic records using a login ID. The students have read access to the information, meaning they can only read the information but cannot edit it. Students can read: Attendance percentage Internal assessment marks Assignment results Seminar evaluation scores This module increases transparency for the students. 11. DATABASE DESIGN : The role of database design in the efficient storage and management of academic data cannot be overstated. For this project, MongoDB is used as the database management system. MongoDB MongoDB is a database management system that belongs to the category of NoSQL databases. This means that the data is stored in a document format. Database Design There are a number of collections in the database, each used to store different data. Users Collection In this collection, the login information of the administrator, faculty, and students is stored. Students Collection In this collection, the information of the students, including student ID, name, and department, is stored. Attendance Collection In this collection, the daily attendance information of the students is stored. Assignments Collection This collection holds information about the assignments and the marks for each student. Internal Marks Collection This collection holds information about the internal assessment data for each student. Seminar Evaluations Collection This collection holds the marks for the student seminar evaluations. 1. ER DIAGRAM EXPLANATION : Entity Relationship Diagram The Entity Relationship (ER) Diagram shows the structure of the database and the relationships among various entities of the system. The major entities of the system include Student, Staff, Attendance, Assignments, Internal Marks, and Seminar Evaluations. Student The Student entity includes various attributes like student ID, name, department, etc. Every student has his/her attendance, assignment marks, and internal marks. Staff Staff members are the faculty of the college. They handle the attendance of the students, the assignment marks of the students, etc. Attendance This entity stores the attendance of the students on a daily basis. This entity is related to the Student entity through the student ID. Assignments This entity stores the details of the assignments given to the students along with the marks obtained by the students for the assignments. Every assignment record is related to a particular student. Internal Marks This entity stores the marks obtained by the students for various subjects. Seminar Evaluations This entity stores the marks obtained by the students for the presentation of the seminars. 2. USE CASE DIAGRAM : The Use Case Diagram shows how different users interact with each other. It helps to understand the application of the application and how each user plays their role. There are three main users of this application. They are as follows: Administrator Faculty Member Student The role of the Administrator includes managing users, setting system settings, and monitoring academic data. The Faculty Member can perform tasks such as recording attendance, updating internal marks, managing assignments, and conducting seminars. The role of the Student includes logging into the application to access their attendance, internal marks, and academic progress. The use case diagram shows how each user can interact with each other. 3. IMPLEMENTATION : The Digital Department Logbook & Academic Management System is based on the MERN stack technology. The MERN stack technology offers a new framework for creating efficient and scalable web applications. The frontend of the Digital Department Logbook & Academic Management System is based on React.js, which offers an interactive and efficient user interface for the system. React components are used to create various dashboards and forms, enabling users to interact with the system easily. The backend of the Digital Department Logbook & Academic Management System is based on Node.js and Express.js, which offer efficient and scalable backend operations for the system. These operations include processing user requests, authenticating users, and interacting with the database. The system is based on the MongoDB database, which stores all the academic records, such as student data, attendance, assignment marks, and seminar evaluations. The system offers efficient and secure authentication options for users. JSON Web Tokens (JWT) are used to verify the users during the login session. Passwords are encrypted using bcrypt and stored in the database. All the above-mentioned technologies have been used to create a reliable and efficient system for managing the department’s academic records. 4. RESULTS AND DISCUSSION : After the implementation of the Digital Department Logbook & Academic Management System, some changes have been observed in the academic record management process. For instance, the faculty members can now record the attendance and marks of the students digitally without the need for maintaining a record. The data will be automatically recorded in the database, thus eliminating the chances of errors. Students can now view the academic performance using the student dashboard. This increases the level of transparency for the students, as they can now keep track of the performance throughout the semester.Using the database, the academic record management has been made easier for the administrators. 5. ADVANTAGES OF THE SYSTEM : * It minimizes manual records * It increases accuracy * It offers a centralized data management system * It increases transparency for students * It saves time for faculty members 6. LIMITATIONS : Drawbacks of using this system: * It requires an internet connection * It may require technical support during installation * Users must be trained to use the system 7. FUTURE ENHANCEMENTS : Possible improvements that can be added to this system in the future include support for a mobile application, integration of biometric devices with attendance, AI-based analysis of performances, and notification for students. 8. REFERENCE : 1. Mokhtar, M. N., Suhaini, S. A., Abdullah, F. H., et al. (2024). A survey of anaesthetic training logbook management among postgraduate students. BMC Medical Education, 24(867). 2. Shafiq, D. A., Marjani, M., Habeeb, R. A., & Asirvatham, D. (2025). Digital Footprints of Academic Success: An Empirical Analysis of Moodle Logs and Traditional Factors for Student Performance. Education Sciences, 15(3), 304. 3. Mustafa, R., & Mustafa, K. (2025). Student Records Management System using IoT. International Journal of Computational and Experimental Science and Engineering. 4. Lontaan, R. J., & Sinadia, A. R. (2024). Design and Development of a Web-Based School Information System. CogITo Smart Journal, 10(2), 593606. 5. Makkaraka, A. M. R. B., Iskandar, A., & Wang, Y. (2024). Design of Web-Based Student Academic Information System. Ceddi Journal of Education, 3(2), 915. 6. Sanchez, L., Penarreta, J., & Soria Poma, X. (2024). Learning Management Systems for Higher Education: A Comparative Study. Discover Education Journal. 7. Kerimbayev, N., Adamova, K., & Shadiev, R. (2025). Intelligent Educational Technologies in Individual Learning: A Systematic Literature Review. Smart Learning Environments Journal. 8. OECD. (2023). OECD Digital Education Outlook 2023: Towards an Effective Digital Education Ecosystem. OECD Publishing. 9. Purnomo, E. N., Imron, A., Wiyono, B. B., & Sobri, A. Y. (2024). Transformation of Digital-Based School Culture and Virtual Learning Environment Integration. Cogent Education Journal. 10. Oxyandi, M., Panduragan, S. L., Said, F. M., & Saputra, M. A. (2023). Use of Electronic Logbook Based on Mobile Learning in Clinical Learning among Students. American Journal of Medical Science and Innovation. 9. CONCLUSION: The Digital Class Log Book System offers an efficient and modern alternative for academic record management for academic institutions. The system replaces the conventional logbook with a digital version that allows lecturers to record daily activities for their classes, attendance, assignments, and internal assessment records in an organized manner. With the implementation of the system, the academic records of the students can be managed securely by the lecturers and the academic institutions. Lecturers can manage the subject records of the students, while the students can view their academic records through the dashboard provided by the system. ______________

Digital Department Logbook & Academic Management System View Abstract & download full text of Digital Department Logbook & Academic Management System Download Full-Text PDF Cite this Pu...

#Volume #15, #Issue #03 #(March #2026)

Origin | Interest | Match

0 0 0 0
Minecraft Issues 🤖
Minecraft Issues 🤖
@minecraft-issues.pixigeko.com
1 day ago

🛠️ MC-306830 is now fixed! (16 hours, 59 minutes) 🛠️

The mouse cursor now changes to the "not allowed" shape when hovering over part of the Creative mode inventory's Survival Inventory tab

➡️ https://bugs.mojang.com/browse/MC-306830

0 1 0 0
2rZiKKbOU3nTafniR2qMMSE0gwZ
2rZiKKbOU3nTafniR2qMMSE0gwZ
@2rzikkbou3ntafnir2qmmse0gwz.activitypub.awakari.com.ap.brid.gy
2 days ago
Deepfake Video Detection using Deep Learning and Ant Colony Optimization **DOI :****https://doi.org/10.5281/zenodo.18983781** Download Full-Text PDF Cite this Publication Dr. R. Kaviarasan, S. Sireesha, G. Dinesh Karthikeyan, K. Sindhura Reddy, 2026, Deepfake Video Detection using Deep Learning and Ant Colony Optimization, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume 15, Issue 03 , March – 2026 * **Open Access** * Article Download / Views: 11 * **Authors :** Dr. R. Kaviarasan, S. Sireesha, G. Dinesh Karthikeyan, K. Sindhura Reddy * **Paper ID :** IJERTV15IS030168 * **Volume & Issue : ** Volume 15, Issue 03 , March – 2026 * **Published (First Online):** 12-03-2026 * **ISSN (Online) :** 2278-0181 * **Publisher Name :** IJERT * **License:** This work is licensed under a Creative Commons Attribution 4.0 International License __ PDF Version View __ Text Only Version #### Deepfake Video Detection using Deep Learning and Ant Colony Optimization Dr. R. Kaviarasan Associate Professor Dept of CSE(CS) RGM College of Engineering and Technology, Nandyal, AP | S. Sireesha UG Scholar Dept of CSE(CS) RGM College of Engineering and Technology, Nandyal, AP | G. Dinesh Karthikeyan UG Scholar Dept of CSE(CS) RGM College of Engineering and Technology, Nandyal, AP | K. Sindhura Reddy UG Scholar Dept of CSE(CS) RGM College of Engineering and Technology, Nandyal, AP ---|---|---|--- Abstract Deepfake videos are a major threat to the authenticity of digital media, as they can be easily manipulated and spread. The current state of the art in deepfake video detection using deep learning techniques has achieved promising results but is faced with several challenges, including overfitting, high computational complexity, and dependence on the dataset used. To overcome these challenges, this paper proposes a deepfake video detection system that combines deep learning techniques with Ant Colony Optimization (ACO), where deep learning is employed for feature extraction and ACO is used for optimal feature selection and hyperparameter optimization. The proposed method improves the accuracy of deepfake video detection while reducing the computational complexity. The experimental results show that the proposed model has achieved an accuracy of about 97%, precision of 96%, recall of 95%, and F1-score of 96%, which are impressive results compared to the identified benchmarks. KeywordsDeepfake videos; Ant Colony Optimization (ACO); precision 1. INTRODUCTION Normally, the production of deepfake videos occurs through the use of advanced artificial intelligence and deep learning approaches, whose production of realistic video material involves the use of faces, lips, and speech. Some of the used models include Generative Adversarial Networks (GANs), autoencoders, and deep learning models like CNNs and transformers. Most of these models are trained through the use of large datasets of genuine videos, making the production of believable videos easier and distinguishing them from the original ones difficult due to the advanced production of the videos. The accessibility and availability of tools for deepfake generation have caused significant impacts on society, media, and cybersecurity. Some potential applications or issues that may cause problems include misinformation, political engineering, identity theft, online fraudulent activities, and social engineering attacks. Such issues may impact reputations, opinions, and the level of trust in general media. Critical fields like journalism, law enforcement, and even national security could also be impacted by the risks associated with the existence of deepfakes. Despite the advancement in the methods of detection, the detection of deepfake videos still presents a challenge. Some of the limitations associated with the previously used methods of detection include overfitting, the associated computational complexity, and the need for the use of datasets. In addition, the use of compressed media and the difficulty experienced in the detection of low-quality and real-world videos also pose a challenge, coupled with the change in the pose of bodies and the image size. The change in the models used for the production of deepfake videos has also been a challenge in the detection of the videos. The highlights of this paper includes: * Deepfake videos can be identified effectively using meta-heuristic approach that is ACO(Ant Colony Optimization). * The ACO approach is been proposed to detect deepfake videos, while ACO will be used for feature selection and hyperparameter optimization. * This will, in turn, assist in identifying features, simplifying the problem, and improving the efficiency of the approach in terms of detection. * The suggested approach may address the challenges in existing detection techniques by generalizing well across data The remaining sections of the paper are organized as follows: Section II describes the literature review of the existing deepfake detection methods. Section III describes the proposed methodology for deepfake detection. Section IV explains the experimentation in terms of the dataset and analysis, also the results are presented based on the analysis. In the final section, i.e., in Section V, the conclusion and future scope for deepfake detection are provided. 2. LITERATURE SURVEY Aryaf Al-Adwan et al. identified a hybrid deep learning model that combines convolutional neural network (CNN) and recurrent neural network (RNN) to detect deep fake videos. The weight and bias values of the CNN and RNN are tuned using particle swarm optimization (PSO), a bio-inspired optimization algorithm. In this method first video frames are preprocessed and extracted, these frames are converted into suitable format for input into the CNN. CNN and RNN are pre-trained on a large dataset of real and deepfake videos to extract features from the video frames. Pre-trained CNN and RNN are fine-tuned on the deepfake video detection task. High accuracy, sensitivity, specificity, and F1 score were attained by the proposed approach when tested on two publicly available datasets: Celeb-DF and the Deepfake Detection Challenge Dataset (DFDC). Specifically, the proposed method achieved an average accuracy of 97.26% on Celeb-DF and an average accuracy of 94.2% on DFDC. The results were compared to other state-of-the-art methods and showed that the proposed method outperformed many. The drawback of this approach – CNN has overfitting risk and sensitivity to input changes – RNN has computational intensity and threshold sensitivity PSO has parameter dependency and iterative complexity. Deressa Wodajo Deressa et al. has proposed a generative convolutional vision transformer (GenConViT) for deepfake video detection , it combines ConvNeXt and Swin Transformer models for feature extraction, and it utilizes an Autoencoder and Variational Autoencoder to learn from latent data distributions. By learning from the visual artifacts and latent data distribution, GenConViT achieves an improved performance in detecting a wide range of deepfake videos. The model is trained and evaluated on DFDC, FF++, TM, DeepfakeTIMIT, and Celeb-DF (v2) datasets. Generative Convolutional Vision Transformer model transforms the input facial images to latent spaces and extracts visual clues and hidden patterns from within them to determine whether a video is real or fake. GenConViT model has two independently trained networks and four main modules: an Autoencoder (AE), a Variational Autoencoder (VAE), a ConvNeXt layer, and a Swin Transformer. The first network includes an AE, a ConvNeXt layer, and a Swin Transformer, while the second network includes a VAE, a ConvNeXt layer, and a Swin Transformer. The first network uses an AE to transform images to a Latent Feature (LF) space, maximizing the models class prediction probability, indicating the likelihood that a given input is a deepfake. The second network uses a VAE to maximize the probability of correct class prediction and minimize the reconstruction loss between the sample input image and the reconstructed image. Both AE and VAE models extract LFs from the input facial images (extracted from video frames), which capture hidden patterns and correlations present in the learned deepake visual artifacts. Pros of this approach – strong performance in deepfake video detection, achieving high accuracy across the tested datasets, identifying a wide range of fake videos while preserving the integrity of media. Cons of this approach computational intensity, performance drops on specific datasets , manual pre-processing requirements. Leandro Cunha et al. propose a hybrid EfficientNet-Gated Recurrent Unit (GRU) network as well as EfficientNet-B0- based transfer learning for video forgery classification. A new PSO algorithm is proposed for hyperparameter search, which incorporates composite leaders and reinforcement learning- based search strategy allocation to mitigate premature convergence. The proposed deepfake detection system consists of three key steps, i.e. – data preprocessing for the extraction of cropped facial regions, – the proposed PSO-based hyperparameter optimization during network training stage and – model establishment using the selected optimal settings and subsequent evaluation using unseen test sam ples. In particular, transfer learning with EfficientNet as the backbone as well as a hybrid EfficientNet-GRU model is studied in conjunction with PSO-based hyperparameter search for synthetic video classification. Pros of this method – PSO-based EfficientNet-GRU and EfficientNet-B0 networks outperform the counterparts with manual and optimal learning configurations yielded by other search methods for several deepfake datasets. Cons of this approach high computational cost , scalability issues because of the large datasets . Hanan Saleh Alhaji et al. proposed an innovative approach to deepfake video detection by integrating features derived from ant colony optimizationparticle swarm optimization (ACO- PSO) and deep learning techniques. The proposed methodology leverages ACO-PSO features and deep learning models to enhance detection accuracy and robustness. Features from ACO-PSO are extracted from the spatial and temporal characteristics of video frames, capturing subtle patterns indicative of deepfake manipulation. These features are then used to train a deep learning classifier to automatically distinguish between authentic and deepfake videos. Pros of this method – achieved an accuracy of 98.91% and an F1 score of 99.12%, indicating remarkable success in deepfake detection. Cons sensitivity to image quality , difficult to handle unreadable or low quality images . Tackhyun Jung et al. proposed a new approach to detect Deepfakes generated through the generative adversarial network (GANs) model via an algorithm called DeepVision to analyze a significant change in the pattern of blinking, which is a voluntary and spontaneous action that does not require conscious effort. It is perform integrity verification through tracking significant changes in the eye blinking pattern of a subject in a video. The proposed method called DeepVision is implemented as a measure to verify an anomaly based on the period, repeated number, and elapsed eye blink time when eye blinks were continuously repeated within a very short period of time. Advantages – detected Deepfakes in seven out of eight types of videos with 87.5% accuracy rate. Disadvantage dataset and bench mark limitations and influence of biological and psychological factors . Andreas R¨ossler et al. propose an automated benchmark for facial manipulation detection. In particular, the benchmark is based on Deep Fakes , Face 2 Face , Face Swap and Neural Tex tures as prominent representatives for facial manipulations at random compression level and size. The benchmark is publicly available and contains a hidden test set as well as a database of over 1.8 million manipulated images. They performed a thorough analysis of data-driven forgery detectors. Current facial manipulation methods can be separated into two categories: facial expression manipulation and facial identity manipulation , It enables the transfer of facial expressions of one person to another per son in real time using only commodity hardware. Advantage high accuracy even with strong video compression. Disadvantage dataset dependency. Hessen Bougueffa Eutamene et al. propose a multimodal framework for deepfake detection with reliable accuracy. This method acquires low-level perceptual features from frames of video, including contrast, brightness, and sharpness, and computes artifact scores for artificial anomaly detection. In parallel, this method produces descriptive frame-level captions, summed up for generating video-level summaries for capturing contextual coherence. For training the model, this method leverages the FaceForensics++ dataset, comprising several techniques of deepFake manipulation, including DeepFake, Face2Face, FaceSwap, as well as NeuralTextures. Metadata comprised of quality measurements, the artifact scores, as well as textual captions, is tokenized, processed by a DeepSeek V2 Lite model, fine-tuned by the Low-Rank Adaptation (LoRA) procedure, as the backbone for classification. Pros it achieved 96.51% accuracy for classifying, by integrating low-level perceptual as well as high-level semantic reason. Cons high computational complexity and sensitive to compression artifacts. Reshma Sunil et al. conducted a comprehensive survey. Deepfakes, which involve the manipulation of image, audio and video to produce highly convincing yet completely fabricated content, present significant risks to media, politics, and personal well-being. To address this increasing problem, their comprehensive survey investigates the advancement along with evaluation of autonomous techniques for identifying and evaluating deepfake media. It provides an in- depth analysis of state-of-the-art techniques and tools for identifying deepfakes, encompassing image, video, and audio- based content. They explored the fundamental technologies, such as deep learning models, and evaluate their efficacy in differentiating real and manipulated media. Advantage provides an in depth analysis of state-of-the-art tools and foundational deep learning techniques across image, video, and audio. Disadvantage as a review paper, it does not propose a single new method but highlights the broad challenge of real time deepfake evolution. Andry Chowanda et al. examined the effectiveness of combining a conventional optimization technique i.e; gradient- based optimization with a metaheuristic search approach i.e; swarm intelligence to improve model performance. An inception-based architecture is utilized to model emotion recognition from facial cues. A hybrid optimization approach that integrates gradient-based and swarm intelligence techniques is employed to improve the architectures. Advantage-combines gradient based and metaheuristic search to improve performance in varying illumination and facial variances, attained a training accuracy of 99.15%,a validation accuracy of 100%. Disadvantage models can be significantly impacted by extreme environmental variances and illumination changes. Sarah Abdulkarem Al-shalif et al. systematically analyzed the MH techniques used for FS between 2015 and 2022, focusing on 108 primary studies from three different databases such as Scopus, Science Direct, and Google Scholar to identify the techniques used, as well as their strengths and weaknesses. MHtechniques are efficient and outperform traditional techniques, with the potential for further exploration of MH techniques such as Ringed Seal Search (RSS) to improve FS in several applications. Pros outperforms traditional statistical methods in finding optimal, reduced feature subsets. Cons high computational complexity compared to simple filter based methods. 3. OVERVIEW OF ANT COLONY OPTIMIZATION The Ant Colony Optimization Algorithm for Deep Fake Detection (ACO_DFD) was designed based on the inspiration of behavior of ant in searching their food particles. The ants usually live in groups and the food that is searched by ants will be useful for the entire ant colony. There are two types of ants in the olony: First in the category is the Queen ant their prime objective is colony reproduction. Second is the Male ant which is used for reproduction and last category is the Worker ant which is responsible for foraging behavior of food. This worker ant behavior is mimicked in the ACO_DFD for effective Deep fake detection. The proposed method falls in the category of Meta-Heuristic and Nature Inspired Algorithm, so always a global solution can be achieved and it will never struck into local optima. It will always attain global solution. The worker ants generally search for food particles and they have to travel long distance. The collected food particles will be stored and used during emergency situations where the ants cannot leave out of their residing place. The multiple worker ants used to go in search of food particles. The ants start to shed a chemical called pheromone. This chemical will be used by other ants to bring travel and bring the food particle back. The shortest path and most frequently used path will have high intensity of pheromone while less used path the pheromone will start to evaporate. From the possible solutions best, optimal solution is selected. The image or video frame is taken as input , gives either 0/1. The value 0 denotes real and 1 denotes fake. The Dataset has total no of N samples and is the input and is the output obtained for the given frame using Equ. (1) (1) The data set that is used in the work is taken from Kaggle website https://zenodo.org/record/5528418#.YpdlS2hBzDd. The next step is involved preprocessing where the raw input frame is extracted V= { F1 , F2,Fn} and it is resized to a dimsension of 256*256. Normalization process has to be carried out for transforming the pixel intensity values into standard numerical values for better convergence. Here min max normalization is used Equ. (2) and (3) (2) (3) The normalization perform linear scaling. So the values are fixed between range of 0 to 1 which helps in active convergence and stable learning. The final processed output is which is shown in Equ.(4) (4) The pheromone Matrix has to be initialized as which is shown in Equ (5) . (5) All the features will get equal pheromone value at the start. Each ant start to select a feature. Initially it is Best= (6) Each ant tries to build a subset solution based on probalistic selection (Equ. 7) using pheromone strength and heuristic desirability. is the Pheromone strength and is the heuristic desirability. a is pheromone importance factor and b is heuristic importance factor. (7) If Higher pheromone and stronger heuristic then it is higher probability. After the construction of the subset the CNN is applied on the selected features and fitness is computed using Equ (8). Where is the selected features and is the penalty variable. n is the total no of system with common computational capabilities, and the model training and testing were done using common deepfake datasets. Performance evaluation metrics like accuracy, F1- score, and AUC were calculated to assess the efficacy of the proposed method over various runs. If , features. (8) Then update Best= and . Update the pheromone trial as better subset will have higher pheromone value. These process like Feature selection, Classification, Fitness evaluation and Pheromone updated is repeated until max iteration is reached or till better convergence is achieved. Algorithm of HWOA Input: Dataset Output: Deepfake Detection D* 1. Preprocess images in Dataset * Detect face * Resize * Normalize pixel values 2. Extract CNN features F 3. Initialize pheromone values P 4. FOR t = 1 to T do FOR each ant k do Select feature subset Sk using P Train detector using Sk Evaluate fitness END FOR Update pheromone values P END FOR 5. Select best feature subset S* 6. Train final detector D* using S* 7. Return D* 4. EXPERIMENTAL RESULTS The proposed deepfake detection model based on deep learning and Ant Colony Optimization (ACO) was developed using Python because of its rich set of libraries and tools for machine learning and image processing tasks. The simulation setup was designed using common deep learning and data processing libraries, where OpenCV was utilized for video frame extraction and preprocessing, including face detection, resizing, and normalization. The CNN model was designed using deep learning libraries like TensorFlow/Keras for extracting spatial features from video frames, and the ACO algorithm was incorporated for feature selection and hyperparameter tuning. The experiments were carried out on a Figure 1. Accuracy Vs Iterations The Accuracy generally mesures the accuracy of the model. In figure 1 the ACO_DFD has obtained an improved accuracy of 5.43% when compared with GA. Figure 2. F1 score Vs Iterations The F1 score is used to balance precession and recall. In the Deepfake detection many of the time the datasets are imbalanced. In figure 2 it is evident that ACO_DFD has an improved F1 score of 6.67% when compared with the existing method GA. Figure 3. AUC Vs Iterations The Area Under ROC tells about the models ability in identifying fake and real images. In figure 3 the ACO_DFD has an improvement of 5.38% when compared with the existing method GA. 5. CONCLUSION The proposed system, Deepfake Video Detection using Deep Learning and Ant Colony Optimization (ACO), proves to be an effective solution for the detection of manipulated video content by leveraging the strong feature extraction capability of deep learning models along with the optimization capabilities of Ant Colony Optimization. Deep learning models, specifically Convolutional Neural Networks (CNNs), are efficient in extracting spatial and temporal irregularities of facial expressions, texture, and frame-level artifacts, which are further optimized by Ant Colony Optimization for better performance. The proposed system is an effective solution for improving the accuracy of detection, minimizing false positives, and maximizing computational efficiency compared to traditional deepfake detection systems. The proposed system of combining deep learning with Ant Colony Optimization is an effective solution for providing a robust and efficient framework for countering the increasing threat of deepfake technology. The proposed system can be applied to various domains, including digital forensics, social media surveillance, cybersecurity, and media validation, for ensuring improved trust and reliability of digital content. In the future, the proposed approach can be extended by using the latest deep learning models like transformers and attention models to improve the accuracy of detection against highly sophisticated deepfakes. Real-time detection approaches can also be designed for use on social media platforms and live streaming services. Moreover, multimodal analysis approaches that use video, audio, and metadata features together can be used to improve the robustness of the approach against the latest deepfake generation methods. Future work can be done to improve the generalization capabilities of the approach on various datasets and to reduce the complexity of the approach for implementation on edge devices. The approach can also be made adaptive to next-generation AI-generated media attacks using reinforcement learning and hybrid optimization approaches, which are not limited to ACO. REFERENCES 1. Z. Pan, W. Yu, X. Yi, A. Khan, F. Yuan, and Y. Zheng, Recent Progress on Generative Adversarial Networks (GANs): a survey, IEEE Access, vol. 7, pp. 3632236333, Jan. 2019, doi: 10.1109/access.2019.2905015. 2. A. H. Soudy et al., Deepfake detection using convolutional vision transformers and convolutional neural networks, Neural Computing and Applications, vol. 36, no. 31, pp. 1975919775, Aug. 2024, doi: 10.1007/s00521-024-10181-7. 3. Y. Patel et al., Deepfake Generation and detection: case study and challenges, IEEE Access, vol. 11, pp. 143296143323, Jan. 2023, doi: 10.1109/access.2023.3342107. 4. F. Folorunsho and B. F. Boamah, deepfake technology and its impact: ethical considerations, societal disruptions, and security threats in ai- generated media, international journal of information technology and management information systems, vol. 16, no. 1, pp. 10601080, feb. 2025, doi: 10.34218/ijitmis_16_01_076. 5. K. T. Pedersen, L. Pepke, T. Stærmose, M. Papaioannou, G. Choudhary, and N. Dragoni, Deepfake-Driven Social Engineering: threats, detection techniques, and defensive strategies in corporate environments, Journal of Cybersecurity and Privacy, vol. 5, no. 2, p. 18, Apr. 2025, doi: 10.3390/jcp5020018. 6. A. Kaur, A. N. Hoshyar, V. Saikrishna, S. Firmin, and F. Xia, Deepfake video detection: challenges and opportunities, Artificial Intelligence Review, vol. 57, no. 6, May 2024, doi: 10.1007/s10462-024-10810-6. 7. A. Al-Adwan, H. Alazzam, N. Al-Anbaki, and E. Alduweib, Detection of deepfake media using a hybrid CNNRNN model and particle swarm optimization (PSO) algorithm, Computers, vol. 13, no. 4, p. 99, Apr. 2024, doi: 10.3390/computers13040099. 8. D. W. Deressa, H. Mareen, P. Lambert, S. Atnafu, Z. Akhtar, and G. Van Wallendael, GENCONVIT: Deepfake video detection using Generative Convolutional Vision Transformer, Applied Sciences, vol. 15, no. 12, p. 6622, Jun. 2025, doi: 10.3390/app15126622. 9. L. Cunha, L. Zhang, B. Sowan, C. P. Lim, and Y. Kong, Video deepfake detection using Particle Swarm Optimization improved deep neural networks, Neural Computing and Applications, vol. 36, no. 15, pp. 84178453, Feb. 2024, doi: 10.1007/s00521-024-09536-x. 10. H. S. Alhaji, Y. Celik, and S. Goel, An approach to deepfake video detection based on ACO-PSO features and deep learning, Electronics, vol. 13, no. 12, p. 2398, Jun. 2024, doi: 10.3390/electronics13122398. 11. T. Jung, S. Kim, and K. Kim, DeepVision: DeepFakes detection using human eye blinking pattern, IEEE Access, vol. 8, pp. 8314483154, Jan. 2020, doi: 10.1109/access.2020.2988660. 12. Andreas R¨ ossler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Nießner, FaceForensics++: Learning to Detect Manipulated Facial Images, Roßler et al., ICCV, 2019. 13. Hessen Bougueffa Eutamene, Wassim Hamidouche, Mamadou Keita, Abdelmalik Taleb-Ahmed, and Abdenour Hadid, Integrating perceptual quality analysis and caption-based features for robust deepfake video detection , Computers and Electrical Engineering , Vol 128, Article 110699, doi: 10.1016/j.compeleceng.2025.110699. 14. Reshma Sunil, Parita Mer, Anjali Diwan, Rajesh Mahadeva, and Anuj Sharma, Exploring autonomous methods for deepfake detection: A detailed survey on techniques and evaluation, Heliyon, 23 January 2025, Volume: 11 2025, Article ID: e42273. 15. A. Chowanda and M. I. B. M. Ariff, CNN-swarm intelligence hybrid model for facial expression recognition, Procedia Computer Science, vol. 269, pp. 844852, Jan. 2025, doi: 10.1016/j.procs.2025.09.027. 16. S. A. Al-Shalif et al., A systematic literature review on meta-heuristic based feature selection techniques for text classification, PeerJ Computer Science, vol. 10, p. e2084, Jun. 2024, doi: 10.7717/peerj-cs.2084. ______________

Deepfake Video Detection using Deep Learning and Ant Colony Optimization View Abstract & download full text of Deepfake Video Detection using Deep Learning and Ant Colony Optimization Download ...

#Volume #15, #Issue #03 #(March #2026)

Origin | Interest | Match

0 0 0 0
2rZiKKbOU3nTafniR2qMMSE0gwZ
2rZiKKbOU3nTafniR2qMMSE0gwZ
@2rzikkbou3ntafnir2qmmse0gwz.activitypub.awakari.com.ap.brid.gy
2 days ago
Deepfake Video Detection using Deep Learning and Ant Colony Optimization **DOI :****https://doi.org/10.5281/zenodo.18983781** Download Full-Text PDF Cite this Publication Dr. R. Kaviarasan, S. Sireesha, G. Dinesh Karthikeyan, K. Sindhura Reddy, 2026, Deepfake Video Detection using Deep Learning and Ant Colony Optimization, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume 15, Issue 03 , March – 2026 * **Open Access** * Article Download / Views: 11 * **Authors :** Dr. R. Kaviarasan, S. Sireesha, G. Dinesh Karthikeyan, K. Sindhura Reddy * **Paper ID :** IJERTV15IS030168 * **Volume & Issue : ** Volume 15, Issue 03 , March – 2026 * **Published (First Online):** 12-03-2026 * **ISSN (Online) :** 2278-0181 * **Publisher Name :** IJERT * **License:** This work is licensed under a Creative Commons Attribution 4.0 International License __ PDF Version View __ Text Only Version #### Deepfake Video Detection using Deep Learning and Ant Colony Optimization Dr. R. Kaviarasan Associate Professor Dept of CSE(CS) RGM College of Engineering and Technology, Nandyal, AP | S. Sireesha UG Scholar Dept of CSE(CS) RGM College of Engineering and Technology, Nandyal, AP | G. Dinesh Karthikeyan UG Scholar Dept of CSE(CS) RGM College of Engineering and Technology, Nandyal, AP | K. Sindhura Reddy UG Scholar Dept of CSE(CS) RGM College of Engineering and Technology, Nandyal, AP ---|---|---|--- Abstract Deepfake videos are a major threat to the authenticity of digital media, as they can be easily manipulated and spread. The current state of the art in deepfake video detection using deep learning techniques has achieved promising results but is faced with several challenges, including overfitting, high computational complexity, and dependence on the dataset used. To overcome these challenges, this paper proposes a deepfake video detection system that combines deep learning techniques with Ant Colony Optimization (ACO), where deep learning is employed for feature extraction and ACO is used for optimal feature selection and hyperparameter optimization. The proposed method improves the accuracy of deepfake video detection while reducing the computational complexity. The experimental results show that the proposed model has achieved an accuracy of about 97%, precision of 96%, recall of 95%, and F1-score of 96%, which are impressive results compared to the identified benchmarks. KeywordsDeepfake videos; Ant Colony Optimization (ACO); precision 1. INTRODUCTION Normally, the production of deepfake videos occurs through the use of advanced artificial intelligence and deep learning approaches, whose production of realistic video material involves the use of faces, lips, and speech. Some of the used models include Generative Adversarial Networks (GANs), autoencoders, and deep learning models like CNNs and transformers. Most of these models are trained through the use of large datasets of genuine videos, making the production of believable videos easier and distinguishing them from the original ones difficult due to the advanced production of the videos. The accessibility and availability of tools for deepfake generation have caused significant impacts on society, media, and cybersecurity. Some potential applications or issues that may cause problems include misinformation, political engineering, identity theft, online fraudulent activities, and social engineering attacks. Such issues may impact reputations, opinions, and the level of trust in general media. Critical fields like journalism, law enforcement, and even national security could also be impacted by the risks associated with the existence of deepfakes. Despite the advancement in the methods of detection, the detection of deepfake videos still presents a challenge. Some of the limitations associated with the previously used methods of detection include overfitting, the associated computational complexity, and the need for the use of datasets. In addition, the use of compressed media and the difficulty experienced in the detection of low-quality and real-world videos also pose a challenge, coupled with the change in the pose of bodies and the image size. The change in the models used for the production of deepfake videos has also been a challenge in the detection of the videos. The highlights of this paper includes: * Deepfake videos can be identified effectively using meta-heuristic approach that is ACO(Ant Colony Optimization). * The ACO approach is been proposed to detect deepfake videos, while ACO will be used for feature selection and hyperparameter optimization. * This will, in turn, assist in identifying features, simplifying the problem, and improving the efficiency of the approach in terms of detection. * The suggested approach may address the challenges in existing detection techniques by generalizing well across data The remaining sections of the paper are organized as follows: Section II describes the literature review of the existing deepfake detection methods. Section III describes the proposed methodology for deepfake detection. Section IV explains the experimentation in terms of the dataset and analysis, also the results are presented based on the analysis. In the final section, i.e., in Section V, the conclusion and future scope for deepfake detection are provided. 2. LITERATURE SURVEY Aryaf Al-Adwan et al. identified a hybrid deep learning model that combines convolutional neural network (CNN) and recurrent neural network (RNN) to detect deep fake videos. The weight and bias values of the CNN and RNN are tuned using particle swarm optimization (PSO), a bio-inspired optimization algorithm. In this method first video frames are preprocessed and extracted, these frames are converted into suitable format for input into the CNN. CNN and RNN are pre-trained on a large dataset of real and deepfake videos to extract features from the video frames. Pre-trained CNN and RNN are fine-tuned on the deepfake video detection task. High accuracy, sensitivity, specificity, and F1 score were attained by the proposed approach when tested on two publicly available datasets: Celeb-DF and the Deepfake Detection Challenge Dataset (DFDC). Specifically, the proposed method achieved an average accuracy of 97.26% on Celeb-DF and an average accuracy of 94.2% on DFDC. The results were compared to other state-of-the-art methods and showed that the proposed method outperformed many. The drawback of this approach – CNN has overfitting risk and sensitivity to input changes – RNN has computational intensity and threshold sensitivity PSO has parameter dependency and iterative complexity. Deressa Wodajo Deressa et al. has proposed a generative convolutional vision transformer (GenConViT) for deepfake video detection , it combines ConvNeXt and Swin Transformer models for feature extraction, and it utilizes an Autoencoder and Variational Autoencoder to learn from latent data distributions. By learning from the visual artifacts and latent data distribution, GenConViT achieves an improved performance in detecting a wide range of deepfake videos. The model is trained and evaluated on DFDC, FF++, TM, DeepfakeTIMIT, and Celeb-DF (v2) datasets. Generative Convolutional Vision Transformer model transforms the input facial images to latent spaces and extracts visual clues and hidden patterns from within them to determine whether a video is real or fake. GenConViT model has two independently trained networks and four main modules: an Autoencoder (AE), a Variational Autoencoder (VAE), a ConvNeXt layer, and a Swin Transformer. The first network includes an AE, a ConvNeXt layer, and a Swin Transformer, while the second network includes a VAE, a ConvNeXt layer, and a Swin Transformer. The first network uses an AE to transform images to a Latent Feature (LF) space, maximizing the models class prediction probability, indicating the likelihood that a given input is a deepfake. The second network uses a VAE to maximize the probability of correct class prediction and minimize the reconstruction loss between the sample input image and the reconstructed image. Both AE and VAE models extract LFs from the input facial images (extracted from video frames), which capture hidden patterns and correlations present in the learned deepake visual artifacts. Pros of this approach – strong performance in deepfake video detection, achieving high accuracy across the tested datasets, identifying a wide range of fake videos while preserving the integrity of media. Cons of this approach computational intensity, performance drops on specific datasets , manual pre-processing requirements. Leandro Cunha et al. propose a hybrid EfficientNet-Gated Recurrent Unit (GRU) network as well as EfficientNet-B0- based transfer learning for video forgery classification. A new PSO algorithm is proposed for hyperparameter search, which incorporates composite leaders and reinforcement learning- based search strategy allocation to mitigate premature convergence. The proposed deepfake detection system consists of three key steps, i.e. – data preprocessing for the extraction of cropped facial regions, – the proposed PSO-based hyperparameter optimization during network training stage and – model establishment using the selected optimal settings and subsequent evaluation using unseen test sam ples. In particular, transfer learning with EfficientNet as the backbone as well as a hybrid EfficientNet-GRU model is studied in conjunction with PSO-based hyperparameter search for synthetic video classification. Pros of this method – PSO-based EfficientNet-GRU and EfficientNet-B0 networks outperform the counterparts with manual and optimal learning configurations yielded by other search methods for several deepfake datasets. Cons of this approach high computational cost , scalability issues because of the large datasets . Hanan Saleh Alhaji et al. proposed an innovative approach to deepfake video detection by integrating features derived from ant colony optimizationparticle swarm optimization (ACO- PSO) and deep learning techniques. The proposed methodology leverages ACO-PSO features and deep learning models to enhance detection accuracy and robustness. Features from ACO-PSO are extracted from the spatial and temporal characteristics of video frames, capturing subtle patterns indicative of deepfake manipulation. These features are then used to train a deep learning classifier to automatically distinguish between authentic and deepfake videos. Pros of this method – achieved an accuracy of 98.91% and an F1 score of 99.12%, indicating remarkable success in deepfake detection. Cons sensitivity to image quality , difficult to handle unreadable or low quality images . Tackhyun Jung et al. proposed a new approach to detect Deepfakes generated through the generative adversarial network (GANs) model via an algorithm called DeepVision to analyze a significant change in the pattern of blinking, which is a voluntary and spontaneous action that does not require conscious effort. It is perform integrity verification through tracking significant changes in the eye blinking pattern of a subject in a video. The proposed method called DeepVision is implemented as a measure to verify an anomaly based on the period, repeated number, and elapsed eye blink time when eye blinks were continuously repeated within a very short period of time. Advantages – detected Deepfakes in seven out of eight types of videos with 87.5% accuracy rate. Disadvantage dataset and bench mark limitations and influence of biological and psychological factors . Andreas R¨ossler et al. propose an automated benchmark for facial manipulation detection. In particular, the benchmark is based on Deep Fakes , Face 2 Face , Face Swap and Neural Tex tures as prominent representatives for facial manipulations at random compression level and size. The benchmark is publicly available and contains a hidden test set as well as a database of over 1.8 million manipulated images. They performed a thorough analysis of data-driven forgery detectors. Current facial manipulation methods can be separated into two categories: facial expression manipulation and facial identity manipulation , It enables the transfer of facial expressions of one person to another per son in real time using only commodity hardware. Advantage high accuracy even with strong video compression. Disadvantage dataset dependency. Hessen Bougueffa Eutamene et al. propose a multimodal framework for deepfake detection with reliable accuracy. This method acquires low-level perceptual features from frames of video, including contrast, brightness, and sharpness, and computes artifact scores for artificial anomaly detection. In parallel, this method produces descriptive frame-level captions, summed up for generating video-level summaries for capturing contextual coherence. For training the model, this method leverages the FaceForensics++ dataset, comprising several techniques of deepFake manipulation, including DeepFake, Face2Face, FaceSwap, as well as NeuralTextures. Metadata comprised of quality measurements, the artifact scores, as well as textual captions, is tokenized, processed by a DeepSeek V2 Lite model, fine-tuned by the Low-Rank Adaptation (LoRA) procedure, as the backbone for classification. Pros it achieved 96.51% accuracy for classifying, by integrating low-level perceptual as well as high-level semantic reason. Cons high computational complexity and sensitive to compression artifacts. Reshma Sunil et al. conducted a comprehensive survey. Deepfakes, which involve the manipulation of image, audio and video to produce highly convincing yet completely fabricated content, present significant risks to media, politics, and personal well-being. To address this increasing problem, their comprehensive survey investigates the advancement along with evaluation of autonomous techniques for identifying and evaluating deepfake media. It provides an in- depth analysis of state-of-the-art techniques and tools for identifying deepfakes, encompassing image, video, and audio- based content. They explored the fundamental technologies, such as deep learning models, and evaluate their efficacy in differentiating real and manipulated media. Advantage provides an in depth analysis of state-of-the-art tools and foundational deep learning techniques across image, video, and audio. Disadvantage as a review paper, it does not propose a single new method but highlights the broad challenge of real time deepfake evolution. Andry Chowanda et al. examined the effectiveness of combining a conventional optimization technique i.e; gradient- based optimization with a metaheuristic search approach i.e; swarm intelligence to improve model performance. An inception-based architecture is utilized to model emotion recognition from facial cues. A hybrid optimization approach that integrates gradient-based and swarm intelligence techniques is employed to improve the architectures. Advantage-combines gradient based and metaheuristic search to improve performance in varying illumination and facial variances, attained a training accuracy of 99.15%,a validation accuracy of 100%. Disadvantage models can be significantly impacted by extreme environmental variances and illumination changes. Sarah Abdulkarem Al-shalif et al. systematically analyzed the MH techniques used for FS between 2015 and 2022, focusing on 108 primary studies from three different databases such as Scopus, Science Direct, and Google Scholar to identify the techniques used, as well as their strengths and weaknesses. MHtechniques are efficient and outperform traditional techniques, with the potential for further exploration of MH techniques such as Ringed Seal Search (RSS) to improve FS in several applications. Pros outperforms traditional statistical methods in finding optimal, reduced feature subsets. Cons high computational complexity compared to simple filter based methods. 3. OVERVIEW OF ANT COLONY OPTIMIZATION The Ant Colony Optimization Algorithm for Deep Fake Detection (ACO_DFD) was designed based on the inspiration of behavior of ant in searching their food particles. The ants usually live in groups and the food that is searched by ants will be useful for the entire ant colony. There are two types of ants in the olony: First in the category is the Queen ant their prime objective is colony reproduction. Second is the Male ant which is used for reproduction and last category is the Worker ant which is responsible for foraging behavior of food. This worker ant behavior is mimicked in the ACO_DFD for effective Deep fake detection. The proposed method falls in the category of Meta-Heuristic and Nature Inspired Algorithm, so always a global solution can be achieved and it will never struck into local optima. It will always attain global solution. The worker ants generally search for food particles and they have to travel long distance. The collected food particles will be stored and used during emergency situations where the ants cannot leave out of their residing place. The multiple worker ants used to go in search of food particles. The ants start to shed a chemical called pheromone. This chemical will be used by other ants to bring travel and bring the food particle back. The shortest path and most frequently used path will have high intensity of pheromone while less used path the pheromone will start to evaporate. From the possible solutions best, optimal solution is selected. The image or video frame is taken as input , gives either 0/1. The value 0 denotes real and 1 denotes fake. The Dataset has total no of N samples and is the input and is the output obtained for the given frame using Equ. (1) (1) The data set that is used in the work is taken from Kaggle website https://zenodo.org/record/5528418#.YpdlS2hBzDd. The next step is involved preprocessing where the raw input frame is extracted V= { F1 , F2,Fn} and it is resized to a dimsension of 256*256. Normalization process has to be carried out for transforming the pixel intensity values into standard numerical values for better convergence. Here min max normalization is used Equ. (2) and (3) (2) (3) The normalization perform linear scaling. So the values are fixed between range of 0 to 1 which helps in active convergence and stable learning. The final processed output is which is shown in Equ.(4) (4) The pheromone Matrix has to be initialized as which is shown in Equ (5) . (5) All the features will get equal pheromone value at the start. Each ant start to select a feature. Initially it is Best= (6) Each ant tries to build a subset solution based on probalistic selection (Equ. 7) using pheromone strength and heuristic desirability. is the Pheromone strength and is the heuristic desirability. a is pheromone importance factor and b is heuristic importance factor. (7) If Higher pheromone and stronger heuristic then it is higher probability. After the construction of the subset the CNN is applied on the selected features and fitness is computed using Equ (8). Where is the selected features and is the penalty variable. n is the total no of system with common computational capabilities, and the model training and testing were done using common deepfake datasets. Performance evaluation metrics like accuracy, F1- score, and AUC were calculated to assess the efficacy of the proposed method over various runs. If , features. (8) Then update Best= and . Update the pheromone trial as better subset will have higher pheromone value. These process like Feature selection, Classification, Fitness evaluation and Pheromone updated is repeated until max iteration is reached or till better convergence is achieved. Algorithm of HWOA Input: Dataset Output: Deepfake Detection D* 1. Preprocess images in Dataset * Detect face * Resize * Normalize pixel values 2. Extract CNN features F 3. Initialize pheromone values P 4. FOR t = 1 to T do FOR each ant k do Select feature subset Sk using P Train detector using Sk Evaluate fitness END FOR Update pheromone values P END FOR 5. Select best feature subset S* 6. Train final detector D* using S* 7. Return D* 4. EXPERIMENTAL RESULTS The proposed deepfake detection model based on deep learning and Ant Colony Optimization (ACO) was developed using Python because of its rich set of libraries and tools for machine learning and image processing tasks. The simulation setup was designed using common deep learning and data processing libraries, where OpenCV was utilized for video frame extraction and preprocessing, including face detection, resizing, and normalization. The CNN model was designed using deep learning libraries like TensorFlow/Keras for extracting spatial features from video frames, and the ACO algorithm was incorporated for feature selection and hyperparameter tuning. The experiments were carried out on a Figure 1. Accuracy Vs Iterations The Accuracy generally mesures the accuracy of the model. In figure 1 the ACO_DFD has obtained an improved accuracy of 5.43% when compared with GA. Figure 2. F1 score Vs Iterations The F1 score is used to balance precession and recall. In the Deepfake detection many of the time the datasets are imbalanced. In figure 2 it is evident that ACO_DFD has an improved F1 score of 6.67% when compared with the existing method GA. Figure 3. AUC Vs Iterations The Area Under ROC tells about the models ability in identifying fake and real images. In figure 3 the ACO_DFD has an improvement of 5.38% when compared with the existing method GA. 5. CONCLUSION The proposed system, Deepfake Video Detection using Deep Learning and Ant Colony Optimization (ACO), proves to be an effective solution for the detection of manipulated video content by leveraging the strong feature extraction capability of deep learning models along with the optimization capabilities of Ant Colony Optimization. Deep learning models, specifically Convolutional Neural Networks (CNNs), are efficient in extracting spatial and temporal irregularities of facial expressions, texture, and frame-level artifacts, which are further optimized by Ant Colony Optimization for better performance. The proposed system is an effective solution for improving the accuracy of detection, minimizing false positives, and maximizing computational efficiency compared to traditional deepfake detection systems. The proposed system of combining deep learning with Ant Colony Optimization is an effective solution for providing a robust and efficient framework for countering the increasing threat of deepfake technology. The proposed system can be applied to various domains, including digital forensics, social media surveillance, cybersecurity, and media validation, for ensuring improved trust and reliability of digital content. In the future, the proposed approach can be extended by using the latest deep learning models like transformers and attention models to improve the accuracy of detection against highly sophisticated deepfakes. Real-time detection approaches can also be designed for use on social media platforms and live streaming services. Moreover, multimodal analysis approaches that use video, audio, and metadata features together can be used to improve the robustness of the approach against the latest deepfake generation methods. Future work can be done to improve the generalization capabilities of the approach on various datasets and to reduce the complexity of the approach for implementation on edge devices. The approach can also be made adaptive to next-generation AI-generated media attacks using reinforcement learning and hybrid optimization approaches, which are not limited to ACO. REFERENCES 1. Z. Pan, W. Yu, X. Yi, A. Khan, F. Yuan, and Y. Zheng, Recent Progress on Generative Adversarial Networks (GANs): a survey, IEEE Access, vol. 7, pp. 3632236333, Jan. 2019, doi: 10.1109/access.2019.2905015. 2. A. H. Soudy et al., Deepfake detection using convolutional vision transformers and convolutional neural networks, Neural Computing and Applications, vol. 36, no. 31, pp. 1975919775, Aug. 2024, doi: 10.1007/s00521-024-10181-7. 3. Y. Patel et al., Deepfake Generation and detection: case study and challenges, IEEE Access, vol. 11, pp. 143296143323, Jan. 2023, doi: 10.1109/access.2023.3342107. 4. F. Folorunsho and B. F. Boamah, deepfake technology and its impact: ethical considerations, societal disruptions, and security threats in ai- generated media, international journal of information technology and management information systems, vol. 16, no. 1, pp. 10601080, feb. 2025, doi: 10.34218/ijitmis_16_01_076. 5. K. T. Pedersen, L. Pepke, T. Stærmose, M. Papaioannou, G. Choudhary, and N. Dragoni, Deepfake-Driven Social Engineering: threats, detection techniques, and defensive strategies in corporate environments, Journal of Cybersecurity and Privacy, vol. 5, no. 2, p. 18, Apr. 2025, doi: 10.3390/jcp5020018. 6. A. Kaur, A. N. Hoshyar, V. Saikrishna, S. Firmin, and F. Xia, Deepfake video detection: challenges and opportunities, Artificial Intelligence Review, vol. 57, no. 6, May 2024, doi: 10.1007/s10462-024-10810-6. 7. A. Al-Adwan, H. Alazzam, N. Al-Anbaki, and E. Alduweib, Detection of deepfake media using a hybrid CNNRNN model and particle swarm optimization (PSO) algorithm, Computers, vol. 13, no. 4, p. 99, Apr. 2024, doi: 10.3390/computers13040099. 8. D. W. Deressa, H. Mareen, P. Lambert, S. Atnafu, Z. Akhtar, and G. Van Wallendael, GENCONVIT: Deepfake video detection using Generative Convolutional Vision Transformer, Applied Sciences, vol. 15, no. 12, p. 6622, Jun. 2025, doi: 10.3390/app15126622. 9. L. Cunha, L. Zhang, B. Sowan, C. P. Lim, and Y. Kong, Video deepfake detection using Particle Swarm Optimization improved deep neural networks, Neural Computing and Applications, vol. 36, no. 15, pp. 84178453, Feb. 2024, doi: 10.1007/s00521-024-09536-x. 10. H. S. Alhaji, Y. Celik, and S. Goel, An approach to deepfake video detection based on ACO-PSO features and deep learning, Electronics, vol. 13, no. 12, p. 2398, Jun. 2024, doi: 10.3390/electronics13122398. 11. T. Jung, S. Kim, and K. Kim, DeepVision: DeepFakes detection using human eye blinking pattern, IEEE Access, vol. 8, pp. 8314483154, Jan. 2020, doi: 10.1109/access.2020.2988660. 12. Andreas R¨ ossler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Nießner, FaceForensics++: Learning to Detect Manipulated Facial Images, Roßler et al., ICCV, 2019. 13. Hessen Bougueffa Eutamene, Wassim Hamidouche, Mamadou Keita, Abdelmalik Taleb-Ahmed, and Abdenour Hadid, Integrating perceptual quality analysis and caption-based features for robust deepfake video detection , Computers and Electrical Engineering , Vol 128, Article 110699, doi: 10.1016/j.compeleceng.2025.110699. 14. Reshma Sunil, Parita Mer, Anjali Diwan, Rajesh Mahadeva, and Anuj Sharma, Exploring autonomous methods for deepfake detection: A detailed survey on techniques and evaluation, Heliyon, 23 January 2025, Volume: 11 2025, Article ID: e42273. 15. A. Chowanda and M. I. B. M. Ariff, CNN-swarm intelligence hybrid model for facial expression recognition, Procedia Computer Science, vol. 269, pp. 844852, Jan. 2025, doi: 10.1016/j.procs.2025.09.027. 16. S. A. Al-Shalif et al., A systematic literature review on meta-heuristic based feature selection techniques for text classification, PeerJ Computer Science, vol. 10, p. e2084, Jun. 2024, doi: 10.7717/peerj-cs.2084. ______________

Deepfake Video Detection using Deep Learning and Ant Colony Optimization View Abstract & download full text of Deepfake Video Detection using Deep Learning and Ant Colony Optimization Download ...

#Volume #15, #Issue #03 #(March #2026)

Origin | Interest | Match

0 0 0 0
NewYork
NewYork
@newyork.activitypub.awakari.com.ap.brid.gy
2 days ago

‘NY Times’ Columnists Hold Roundtable To Determine What’s Wrong With Them NEW YORK—In a recorded discussion posted to the newspaper’s YouTube channel, opinion columnists for The New York...

#News #Media #Vol #62: #Issue #9

Origin | Interest | Match

0 0 0 0
Minecraft Issues 🤖
Minecraft Issues 🤖
@minecraft-issues.pixigeko.com
2 days ago

🛠️ MC-306064 is now fixed! (41 days, 22 hours, 18 minutes) 🛠️

Mobs can be forced to look like they're dying while they aren't by using commands

➡️ https://bugs.mojang.com/browse/MC-306064

0 0 0 0
✨️Night4Wolfie🌙
✨️Night4Wolfie🌙
@night4wolfie.bsky.social
3 days ago

Hello,
I really need help with my brain rot
I had good idea what to draw but...what.
Also others things is that im really not sure if im coming back to live streaming at this point it just seem stressful and I really hope you guys understand....
#Rot #art #Twitch #issue

2 0 0 0
Minecraft Issues 🤖
Minecraft Issues 🤖
@minecraft-issues.pixigeko.com
3 days ago

🛠️ MC-306709 is now fixed! (8 days, 13 hours, 48 minutes) 🛠️

Librarians' master level book trade is no longer guaranteed when Villager Trade Rebalance is enabled

➡️ https://bugs.mojang.com/browse/MC-306709

0 0 0 0
Minecraft Issues 🤖
Minecraft Issues 🤖
@minecraft-issues.pixigeko.com
3 days ago

🛠️ MC-306626 is now fixed! (14 days, 12 hours) 🛠️

The adult horse's old black dots markings aren't included in the "Programmer Art" resource pack

➡️ https://bugs.mojang.com/browse/MC-306626

0 0 0 0
Thimo Koolen
Thimo Koolen
@thimok.bsky.social
3 days ago

Hey everyone! What's the best way to handle an unexpected production issue as a team? #Software #Engineer #SoftwareEngineering #Code #Production #Issue #Outage #Bug

2 0 3 0
Minecraft Issues 🤖
Minecraft Issues 🤖
@minecraft-issues.pixigeko.com
3 days ago

🛠️ MC-306601 is now fixed! (14 days, 22 hours, 14 minutes) 🛠️

The IME pre-edit window appears in the unfocused text box of the anvil UI when no items are placed in the anvil slots

➡️ https://bugs.mojang.com/browse/MC-306601

0 0 0 0
Minecraft Issues 🤖
Minecraft Issues 🤖
@minecraft-issues.pixigeko.com
3 days ago

🛠️ MC-306516 is now fixed! (20 days, 10 hours, 47 minutes) 🛠️

G-Sync cannot be enabled in the new borderless window mode

➡️ https://bugs.mojang.com/browse/MC-306516

0 0 0 0
LLMs
LLMs
@llms.activitypub.awakari.com.ap.brid.gy
3 days ago
Consumer Attitude Towards AI-Generated Advertisement **DOI :****https://doi.org/10.5281/zenodo.18959491** Download Full-Text PDF Cite this Publication Shaily Raj, Dr. Sabeeha Fatima, 2026, Consumer Attitude Towards AI-Generated Advertisement, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume 15, Issue 03 , March – 2026 * **Open Access** * Article Download / Views: 16 * **Authors :** Shaily Raj, Dr. Sabeeha Fatima * **Paper ID :** IJERTV15IS030352 * **Volume & Issue : ** Volume 15, Issue 03 , March – 2026 * **Published (First Online):** 11-03-2026 * **ISSN (Online) :** 2278-0181 * **Publisher Name :** IJERT * **License:** This work is licensed under a Creative Commons Attribution 4.0 International License __ PDF Version View __ Text Only Version #### Consumer Attitude Towards AI-Generated Advertisement Shaily Raj Student Amity University Lucknow Under Guidance Of: Dr. Sabeeha Fatima Assistant Professor, Amity Business School, Amity University Uttar Pradesh Lucknow Abstract – Generative Artificial Intelligence and its increasing integration in the advertising market have transformed both the deployment and creation of marketing content. Although AI-generated advertisements provide competitive advantages like cost efficiency, scalability and personalization but, the effectiveness ultimately depends on consumer perception and attitude. This study helps to understand consumer awareness of AI-generated advertisements, the stimulus-based responses before and after disclosure of AI involvement, it also analyzes perceived efficiency and overall attitude. Data was collected first handed through a structured online questionnaire. As the world is moving towards AI, the findings indicate high awareness of AI-generated advertising and favorable psychological-based evaluations prior to disclosure except for the shifts in perception, particularly in relation to trust and authenticity. Perceived efficiency was evaluated positively in terms of message clarity and communication effectiveness, though emotional resonance remained a consideration. Respondents preferred transparency and had the overall cautiously positive attitude toward AI-generated with acknowledging future growth prospects. The study emphasizes the fact that consumer perception and attitude are crucial factors in determining the effectiveness of advertising in technologically mediated environments. CHAPTER: 1 – INTRODUCTION Artificial intelligence (AI) is technology that enables computers and machines to simulate human learning, comprehension, problem solving, decision making, creativity and autonomy. AI helps computers analyze and interpret data to perform various intellectual tasks, such as speech recognition, live translation, problem-solving, and even decision-making, almost imitating human-like behavior. Traditional AI was already a huge advancement in the digital world, and with the emergence of Generative AI (GenAI), it gave users the power to create new and unique content in seconds, popularizing its usage across different industries. The public release of the Gen AI tool ChatGPT in late 2022 increased public awareness and use of generative AI in different fields, from using it for academic work to even for professional work. This increase in usage of AI tools has led to the adoption and acceptance of the integration of these tools in various marketing activities, including content targeting, optimization, personalization, and other activities, as AI's ability to identify patterns in large datasets helps marketers to be more relevant and effective. Now, this integration of AI has also been adopted in the creative process of advertising, including the production of ads using Gen AI. This integration may help lower the cost and the production time, but it also raises concerns about the consumers' perception and their attitude. An automated ad might be viewed as less genuine, which can further negatively influence the consumer perception. Consumer perception can directly influence the attitude of a consumer, which can further shape their purchasing behavior. Consumer attitude reflects the positive or negative evaluation of the consumer towards a product or brand. A brand's advertising campaigns or even a single advertisement can help consumers shape their attitude towards the brand. Hence, studying the impact of this Gen AI integration in the creation process of these advertisements on the attitude of consumers becomes vital. This study aims to explore and evaluate this impact on the minds of todays consumers who are generally aware of AI and ethical concerns that comes with its usage. CHAPTER: 2 – LITERATURE REVIEW 1. Baldassarre (2024). The article discusses how artificial intelligence shifted from being a supporting tool to becoming one of the primary tools in digital advertising strategy. The article talks about how AI is now shaping the entire advertising cycle, starting from targeting to performance optimization rather than just focusing on automation. The brands are able to deliver more relevant ads and can also adjust campaigns in real-time with the help of AI systems' ability to analyze large volumes of data quickly and even identify behavioral patterns that can be difficult to detect manually. A key takeaway from this article is that AI not only improves efficiency but also changes the way effectiveness is measured. An AI system enables advertisers to focus on engagement quality and predictive performance instead of simply tracking impressions or clicks. The article suggests that successful integration of AI tools helps brands optimize budgets, refine targeting precision, and respond more quickly to shifts in consumer behavior. The article also implies that while AI automation can increase speed and scale, human strategic thinking still remains important for setting objectives and interpreting results. 2. Babatunde et al. (2024). The study examines how personalization strategies can be enhanced with the use of artificial intelligence in the modern marketing environments. The authors argue that with the ability to analyze large-scale consumer data, hyper-personalized communication can be achieved, which further results in an increase in relevance and customer engagement. They also emphasized on how AI-powered personalization strengthens customer-brand interaction, enhances consumer experience, and contributes to higher engagement rates. Lastly, they also highlighted the concerns regarding data privacy, ethical transparency, and algorithmic bias. 3. Gao et al. (2023). The study focuses on four critical elements of AI advertising: Targeting, Personalization, Content Creation, and Optimization uncovering mutual influences among these elements. It explains how AI can improve advertising precision by helping marketers better identify and understand consumer needs. Personalization helps increase user engagement and is closely related to content creation, for which AI can be used to produce advertising content that aligns with the consumer preferences. The study also discusses about how optimization can also be automated by AI through machine learning and big data analysis. In this process, targeting helps in identifying the main audience, the type of advertisement to be displayed is determined by personalization and lastly optimization helps adjust the factors, including timing and frequency, in order to improve advertising outcomes. 4. Buder and Unfried (2025). This report revealed a gap between the familiarity with generative AI and actual trust of consumer in the use of AI within marketing communications. The survey conducted by them showed that half of the consumers showed awareness towards the ability of AI to generate marketing content whereas only one-quarter were aware that AI uses personal data for personalized content or were confident in recognizing AI-generated materials. Furthermore, the survey also showed very low trust levels of consumers towards use of AI in marketing and in AI itself. These low trust levels indicated that awareness does not translate into acceptance. They also highlighted that policies aiming for transparency may lead in increase in consumer skepticism instead of reducing it. Lastly, the authors suggested that businesses to proactively shape cnsumer attitudes towards AI in order to face this challenge of skepticism. 5. Zhang and Hur (2025). The study explored the impact of disclosure of the use of AI in the creation of an advertisement on consumers' perception. They revealed that under conditions of non-disclosure, the consumers could not identify any significant differences between AI-generated and human- made images and also found them comparable. They also highlighted the concern of consumers about ethical issues, including racial and gender stereotyping and possible job displacement, which can be associated with the usage of AI, further increasing these concerns. Finally. Their findings revealed that disclosure need not inevitably undermine advertising effectiveness. When AI use is strategically framed with appropriate justifications, consumer acceptance can be preserved even under full disclosure . Suggesting that approaches like using AI within framework of consumer benefit and ethical responsibility rather than concealing AI use helps create a balance between innovation and consumer protection needs potentially transforming disclosure from a defensive necessity into a trust-building opportunity . 6. Wang (2025). The article explores the main reason for the failure of high profile AI-Generated holiday advertising campaigns by major global brands such as McDonalds and Coca-Cola in resonating with the audiences. The author highlighted the criticism, for lacking an emotional depth, collected by these ads in context, like the holiday season, in which emotional connection and cultural relevance are crucial elements for audience engagement. The article talks about how the online backlash and criticism were focused on a mix of factors like aesthetic, ethical, emotional and economical factors. Even with the involvement human in creative process for giving the prompts they still cant control the translation of the ideas in the final output. This obscured human involvement in the creative process might lead to a work that is more likely to be perceived as impersonal and inauthentic. Wang concludes that the framing of the content with the guidance and integration with human insight, preserving emotional authenticity while using AI strengths, are the factors that decide the success of AI in creative fields. CHAPTER: 3 1. Research Objectives The main purposes of this study are: * To analyze the level of consumers awareness with integration of AI in advertising and in AI itself. * To examine consumer perception towards AI and use of AI in advertising. * To access change in consumer perception post-disclosure of AI integration. * To examine perceived efficiency of AI-generated ads. * To evaluate overall consumer attitude towards AI-generated ads and its future scope. 2. Research Methodology As prior research has investigated various aspects of consumer perception toward usage of AI tools for generating marketing content, including emotional connect of consumers, their perception, trust and ethical concerns, and disclosure effects. There still remains a gap in observed evidence on consumer awareness, stimulus evaluation and perceived efficiency. Hence, an exploratory primary research design with a pilot-scale sample is adopted for the research to generate additional evidence within the existing but still emergent field of research. * Sampling Technique A pilot-sized sample of consumers from tier 2 and tier 3 cities, those are digitally active, regularly exposed to online advertising and aware of AI. * Data Collection Instrument A structured questionnaire was developed for the study, and an online survey was conducted using the questionnaire. The questionnaire was divided into four sections, with each section having its own main objective. The first section included questions collecting demographic details, and the second section collected data regarding the awareness of AI-generated ads and questions regarding an AI-generated ad stimulus that was attached to record the first reaction of the consumers before disclosing the use of AI. In the third section, the disclosure of the Ad being AI-generated was given, and then questions regarding change in perception were asked. The last section was focused on exploring the perceived efficiency and overall attitude of the consumers. The stimulus provided pre-disclosure of AI use, allowing respondents to evaluate the advertisement without any influence of pre-existing bias. Further change in perception of the respondents after the disclosure of the use of AI was measured. Coca- Cola Holidays are coming ad, which is a disclosed AI generated ad, was used as the stimulus for the study. * Variable and Measurement The study focused on measuring constructs including awareness of AI-generated advertisements; stimulus-based evaluation to evaluate visual appeal, credibility, creativity and purchase interest; post-disclosure perception to analyze trust and ethical concerns of the consumers; perceived efficiency, analyzing the message clarity, influence on decision-making, communication effectiveness; and overall attitude of consumers. The assessment of all constructs was done using multiple five point likert-scale items. * Data Analysis Techniques Statistical tools, including percentage analysis were used for demographic profiling and mean-score analysis for the evaluation of construct-level perceptions was employed for the analysis of the collected data. 3. Limitations 1. Relatively small sample size: Although the study is pilot in nature, the small sample size can limit the generalizability of the results. 2. Generalizability of the findings: The sample was largely composed of respondents of Generation Z, which may affect the ability to estimate and generalize the perception of other age groups. Further, the respondents were shown only one advertisement as a stimulus for evaluation, which limits the generalizability of the results for other types of advertisements or product categories. 3. Reliability of the responses: As all the responses collected were self-reported, this may decrease the reliability of representing actual behavior. CHAPTER: 4 – RESULTS The final analysis was done on a total of 48 responses collected. A strong representation of Generation Z was observed as the majority of respondents, 70.8 per cent, were between the ages of 18 and 25. The remaining 16.7 per cent were aged 26 to 31, and 12. Percent fell within the age group of 45 to 55. The predominance of younger respondents is significant, as prior research suggests that younger cohorts demonstrate higher digital media engagement and greater exposure to algorithm-driven content (Pew Research Center, 2022). The presence of responses of Generation X helps explore the perspective of individuals with the experience of both traditional and digital advertising paradigms, which also adds a comparative depth to the sample. The first part of the examination included consumer awareness of AI-generated advertisements, and to ensure a meaningful evaluation, familiarity with the concept is essential. A mean score of 4.17 on the five-point Likert scale was recorded. In interpreting 5-scale Likert data, mean values above the scale mid-point, 3.0, are generally interpreted as reflecting agreement, while higher mean values indicates stronger level of agreement. Therefore, a mean of 4.17 reflects a clearly positive level of awareness. This positive awareness of AIgenerated ads is also supported by the response distribution, as 7 per cent of respondents either agreed or strongly agreed to having an understanding of AI-generated advertisements, while 83 per cent reported having encountered such ads in digital spaces. A minority of only 6 per cent indicated disagreement regarding familiarity. This relativity low proportion of negative or neutral responses suggests that the strong agreement or higher mean is not driven by extreme outliners but it rather reflects the consistent agreements across the responders. This evaluation indicates that digitally active consumers are more likely to recognize and understand AI-generated ads rather than perceiving it as an unfamiliar or abstract innovation. The following stage of the analysis explored stimulus based evaluation pre-disclosure. Respondents were presented with an AI- generated advertisement as a stimulus without disclosing the production method used to avoid bias. The calculated mean score of the overall evaluation was 3.94 on likert five-point scale; this indicates a generally favorable perception as the value is lying above the neutrality. A further insight can be gathered through percentage distributions with 72 percent of respondents either agreeing or strongly agreeing to the advertisement having a visual appeal while 68 percent of the respondents also found the ad creative, and percent verified its effectiveness in capturing their attention. About 59 percent of responders even agreed that the advertisement is capable to influence their purchase consideration, whereas 17 percent expressed disagreement and 24 percent remained neutral. These figures highlight higher rating for aesthetic and attention- related aspects than persuasive influence. The slightly lower agreement regarding purchase influence, despite the majority viewing the advertisement favorably, suggests that consumers may differentiate between creative appreciation and behavioral persuasion. The overall pattern can be interpreted as positive in terms of aesthetic and communication performance. After the initial evaluation, respondents were informed about the advertisement being AI-generated. This disclosure helped to measure any change in perception after the revelation of the involvement of AI. The mean score was calculated to be 3.56 for the post disclosure related responses. Although following the established likert interpretation conventions, values between 3.5 and 4.0 indicate moderate agreement, the reduction of the score from 3.94 in pre- disclosure to 3.6 post disclosure suggests a measurable moderation effect. This can also be further verified through percentage distribution, as 42 percent that the disclosure changed their perception, while 25 percent respondents disagreed, and 33 percent remained neutral. Moving to trust, 34 percent respondents agreed that their trust was reduced after disclosure, whereas 37 percent expressed to have no change in perception regarding trust, and 29 per cent were neutral. At the same time, 61 percent respondent expressed that a clear disclosure of AI involvement should be provided, reflecting a preference for transparency. These distributions clearly indicate that disclosure did not produce blatant rejection but introduced critical reassessment. The evaluation of perceived efficiency of AI generated ads factors, including message clarity, influence on decision making and communication effectiveness, were taken into consideration. The mean score of perceived efficiency was calculated to be 3.55, indicating a moderate agreement suggesting that AI-generated ads are generally considered as functional by the respondents. This interpretation can be The mean score for overall attitude toward supported by the response distribution, with 65 percent agreeing with AI generated ads having ability to communicate marketing message clearly, while 57 percent even expressing that such advertisement may influence consumer decision. The mean score of 3.74 was calculated regarding the overall attitude toward AI generated advertisement. The proportion distribution showed that almost 62 percent of respondents were open to engage with such advertisement while 70 percent agreed that AI generated advertisement will become more common in the coming future, while only 8 percent clearly disagreed with statements suggesting future acceptance. These figures indicate that immediate evaluation may be influenced by ethical concerns and trust considerations, the future expectations regarding the integration of AI in advertising are not diminished by them and transparency remains as the priority. Lastly Ai-generated advertising appeared to be normalized as a component of marketing communication by the consumers. CHAPTER: 5 – CONCLUSION This study examines consumer awareness, attitude perception, and perceived efficiency of AI-generated advertisements in the era of increasing technological integration in marketing activities. It aims to provide a more refined understanding of how consumers evaluate AI-generated marketing content and what factors these consumers priorities while evaluating such content. The findings indicate a high level of awareness of consumers towards AI-generated ads, and when evaluated without disclosure, the advertisement was perceived positively in terms of visual appeal and communicative clarity. The disclosure did not drastically change the responses as they remain moderate rather than severely negative, suggesting that these ads are not inherently rejected by consumers, while trust and transparency-related concern may arise with this Ai integration. The findings confirm that AI-generated advertisements are not inherently rejected by consumers. The results of this study both slightly support and slightly challenge the existing narratives. While the prior research emphasized strong skepticism and a decrease in effectiveness with perceived artificiality, the findings of this study suggested a phase of cautious normalization. With only a moderate decline in trust post-disclosure, instead of a purely negative decline. The increase in consumer familiarity with AI technologies may be the reason for a more rational evaluation observed than in the earlier studies. This slight divergence from the strongly negative perception in prior research to somewhat moderate perception may be attributed to the increase in familiarity and rapid normalization of AI tools in everyday contexts, suggesting that with more exposure and strategic application, the perceived threat of AI-generated content may diminish. This also indicated a dynamic nature of consumer attitude toward AI in advertising, rather than a static one. Importantly, this study reinforces the importance of consumer attitude and perception while determining advertising effectiveness, just as technological efficiency does not guarantee success. The findings suggested that even with the agreement of the respondents with the functional effectiveness of the ad, the issues related to authenticity, trust, and transparency remain the priority of the consumers. AI-generated advertising appears to be entering a stage of conditional acceptance rather than blatant rejection. While the concerns regarding transparency, trust and authenticity remain, digitally active consumers still demonstrate openness toward a continued integration of AI. The long-term effectiveness of AI integration in advertising hence will depend not only on improving algorithmic sophistication but also on ethical integration and the alignment with consumer expectation of transparency, credibility, and emotional resonance. REFERENCES 1. AI in Advertising: Use Cases, Benefits, & Challenges. (n.d.). Salesforce Web Site: 2. https://www.salesforce.com/media/artificial-intelligence/ai-in-advertising/ 3. AI ads work best when they do not look like AI: Study. (2026, Jan 30). Brand Equity Web Site: 4. https://brandequity.eonomictimes.indiatimes.com/news/digital/ai-generated-ads-why-they-need-to-look-human-to-succeed/127793624 5. Artificial Intelligence In Marketing Market (2025 – 2030): Size, Share & Trends Analysis Report By Component (Software, Services), By Application (Social Media Advertising, Search Engine Marketing), By Technology, By End User Industry, By Region, And Segment Forecasts. (n.d.). Grand View Research Web Site: 6. https://www.grandviewresearch.com/industry-analysis/artificial-intelligence-marketing-market-report/methodology 7. Babatunde, S., Odejide, O., Edunjobi, T., and Ogundipe, D. (2024, Mar 27). THE ROLE OF AI IN MARKETING PERSONALIZATION: A THEORETICAL EXPLORATION OF CONSUMER ENGAGEMENT STRATEGIES. International Journal of Management & Entrepreneurship Research: 8. file:///C:/Users/honda/Downloads/THE_ROLE_OF_AI_IN_MARKETING_PERSONALIZATION_A_THEO.pdf 9. Baldassarre, R. (2024, Apr 09). How AI Is Revolutionizing Digital Advertising In 2024. Forbes: 10. https://www.forbes.com/councils/forbesagencycouncil/2024/04/09/how-ai-is-revolutionizing-digital-advertising-in-2024/ 11. Burder, F., and Unfried, M. (2025). Transparency Without Trust 12. The Impact of Consumer Skepticism of AI-Generated Marketing Content. NIM: 13. https://www.nim.org/en/research/projects-overview/detail-research-project/transparency-without-trust 14. Chui, M., Roberts, R., Yee, L., Hazan, E., Singla, A., Smaje, K., Sukharevsky, A., and Zemmel, R. (2023, Jun 14). The economic potential of generative AI: The next productivity frontier. McKinsey & Company: 15. https://www.mckinsey.com/capabilities/tech-and-ai/our-insights/the-economic-potential-of-generative-AI-the-next-productivity-frontier#business-value 16. Coca-Cola. (2025, Nov 3). Coca-Cola | Holidays Are Coming [Video]. YouTube: https://www.youtube.com/watch?v=Yy6fByUmPuE 17. Consumer Behaviour: What is perception in Consumer Behaviour?. (2025, Oct 10). Kentrix.ai Web Site: 18. https://kentrix.ai/what-is-perception-in-consumer-behaviour/ 19. Dimitrieska, S. (2024, Jun 25). Generative Artificial Intelligence and Advertising. Trends in Economics, Finance and Management Journal: 20. https://tefmj.ibupress.com/uploads/2024/07/ibu_journal_tefmj-3.pdf 21. Duggal, R. (2019, Apr 19). Consumer Attitudes: A Small Factor That Makes A Big Impact. Forbes: 22. https://www.forbes.com/councils/forbescommunicationscouncil/2019/04/19/consumer-attitudes-a-small-factor-that-makes-a-big-impact/ 23. Estévez, M. and Fabrizio, D. (2014) Advertising Effectiveness: An Approach Based on What Consumers Perceive and What Advertisers Need. Open Journal of Business and Management: 24. https://pdfs.semanticscholar.org/acb5/86561076dd56652ffc2aee8caeeee385b444.pdf 25. Exner, Y., Hartmann, J., Netzer, O., Zhang, S., and Ding, Z. (2025, Dec 30). AI in Disguise Quasi-Experimental Analysis of a Large-Scale Deployment of AI-Generated Display Ads. Marketing Science Institute Working Paper Series: 26. https://www.msi.org/working-paper/ai-in-disguise-quasi-experimental-analysis-of-a-large-scale-deployment-of-ai-generated-display-ads/ 27. Gao, B., Wang, Y., Xie, H., Hu, Y., and Hu, Y. (2023, Nov). Artificial Intelligence in Advertising: Advancements, Challenges, and Ethical Considerations in Targeting, Personalization, Content Creation, and Ad Optimization. Sage Publications: 28. https://www.researchgate.net/publication/376094347_Artificial_Intelligence_in_Advertising_Advancements_Challenges_and_Ethical_Considerations_in_Ta rgeting_Personalization_Content_Creation_and_Ad_Optimization 29. Gu, C., Jia, S., Lai, J., Chen, R., and Chang, X. (2024, Sep 3). Exploring Consumer Acceptance of AI-Generated Advertisements: From the Perspectives of Perceived Eeriness and Perceived Intelligence. MDPI: 30. https://www.mdpi.com/0718-1876/19/3/108 31. Niosi, A. (2021). Introduction to Consumer Behaviour: Understanding Attitudes. BCcampus: 32. > Understanding Attitudes 33. Routley, N. (2023, Feb 6). What is generative AI? An AI explains. World Economic Forum: 34. https://www.weforum.org/stories/2023/02/generative-ai-explain-algorithms- work/?gad_source=1&gad_campaignid=22228224717&gbraid=0AAAAAoVy5F7rp1FP1b7zu- TVaIQQls1gZ&gclid=Cj0KCQiAhtvMBhDBARIsAL26pjHWbPvqTMbUFiG2kG727VqNkHpC-DaGDPJYbV-oYN70a9Q63qqEfEcaAjQAEALw_wcB 35. Stryker, C. and Kavlakoglu, E. (2025, Nov 17). What is artificial intelligence (AI)?. IBM: https://www.ibm.com/think/topics/artificial-intelligence 36. Tanwar, P., Antonyraj, S., and Shrivastav, R. (2024, May 5). A Study of Rise of AI in Digital Marketing. IJMRSET: 37. file:///C:/Users/honda/Downloads/A_Study_of_Rise_of_AI_in_Digital_Marketing.pdf 38. Wang, C., Liu, T., Zhu, Y., Wang, H., Wang, X., and Zhao, S. (2023, Nov). The influence of consumer perception on purchase intention: Evidence from cross-border E-commerce platforms. Heliyon: 39. https://www.sciencedirect.com/science/article/pii/S2405844023088254 40. Wang, H. (2025, Dec 19). Why AI-Generated Holiday Ads Fail And What They Teach Us About Using AI in UX Work. NN Group: 41. https://www.nngroup.com/articles/ai-ad/ 42. Zhang, L. and Hur, C. (2025, Oct 16). The Impact of Generative AI Images on Consumer Attitudes in Advertising. Administrative Sciences: 43. https://www.mdpi.com/2076-3387/15/10/395 ______________

Consumer Attitude Towards AI-Generated Advertisement View Abstract & download full text of Consumer Attitude Towards AI-Generated Advertisement Download Full-Text PDF Cite this Publication Shai...

#Volume #15, #Issue #03 #(March #2026)

Origin | Interest | Match

0 0 0 0
Minecraft Issues 🤖
Minecraft Issues 🤖
@minecraft-issues.pixigeko.com
3 days ago

🛠️ MC-306564 is now fixed! (17 days, 26 minutes) 🛠️

Item entities' health does not decrease uniformly when on cacti

➡️ https://bugs.mojang.com/browse/MC-306564

1 1 0 0
ProgressiveAF
ProgressiveAF
@starlinkdidit.bsky.social
4 days ago
Video thumbnail

@snapchatsupport.bsky.social #snapchat #content #quality #issue #censorship

2 0 1 0
LLMs
LLMs
@llms.activitypub.awakari.com.ap.brid.gy
4 days ago
Digital Fortresses Under Siege: Cybercrime in Cameroon’s Banking Sector and the Forensic Accounting Imperative **DOI :****https://doi.org/10.5281/zenodo.18938522** Download Full-Text PDF Cite this Publication Olutimo Oluremi Stephen, Mokube Mathias Itoe, 2026, Digital Fortresses Under Siege: Cybercrime in Cameroon’s Banking Sector and the Forensic Accounting Imperative, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume 15, Issue 03 , March – 2026 * **Open Access** * Article Download / Views: 1 * **Authors :** Olutimo Oluremi Stephen, Mokube Mathias Itoe * **Paper ID :** IJERTV15IS030145 * **Volume & Issue : ** Volume 15, Issue 03 , March – 2026 * **Published (First Online):** 10-03-2026 * **ISSN (Online) :** 2278-0181 * **Publisher Name :** IJERT * **License:** This work is licensed under a Creative Commons Attribution 4.0 International License __ PDF Version View __ Text Only Version #### Digital Fortresses Under Siege: Cybercrime in Cameroon’s Banking Sector and the Forensic Accounting Imperative A Comprehensive Analysis of Threats, Vulnerabilities, and Remedial Pathways Olutimo Oluremi Stephen, PhD Highstone International University Address: 2108 N ST STEN Sacramento, California USA Mokube Mathias Itoe, PhD Address: Cameroun Office: Highstone International University, Nsam Yaounde Institutional Affiliation: Highstone International University, Address: 2108 N ST STEN Sacramento, California USA Conflict of Interest Statement: The authors declare no conflict of interest. Funding: This research received no specific grant from any funding agency. Abstract – Background: Cameroon’s banking sectorincluding commercial banks, microfinance institutions, and mobile money operators #### – is undergoing rapid digital transformation. This growth has improved financial inclusion, particularly through mobile money adoption, yet it has simultaneously exposed the sector to unprecedented cyber threats. In 2025, the Cameroonian government reported losses exceeding 1.027 billion FCFA due to online scams, including phishing, fraudulent investment platforms, SIM swap attacks, and mobile money fraud targeting both individuals and corporate accounts ([Cameroon Intelligence Report, 2025, Biya regime loses over CFA1 billion to cybercrime in 2025, https://www.cameroonintelligencereport.com/biya-regime-loses-over-cfa1-billion-to-cybercrime-in- 2025/?utm_source=chatgpt.com]). While anti-cybercrime legislation has existed since 2010, enforcement remains constrained by limited technical expertise, inadequate training, and institutional resource gaps ([INTERPOL, 2024, Major cybercrime operation nets 1,006 suspects across Africa, https://www.interpol.int/News-and-Events/News/2024/Major-cybercrime-operation-nets-1-006-suspects]). The rising frequency and sophistication of attacks, including fraudulent mobile money transfers averaging 25 million FCFA per incident, underscores the urgent need for enhanced fraud detection and investigation mechanisms. #### Objective: This study investigates the scale, typology, and consequences of cybercrime targeting Cameroon’s banking sector and explores how forensic accounting techniques can strengthen detection, investigation, and prevention efforts. Specifically, it aims to: (1) quantify losses and identify predominant cybercrime modalities, (2) assess existing institutional and legal frameworks, including the 2024 Data Protection Law, and (3) propose a context-specific forensic accounting framework to enhance operational and regulatory cybersecurity measures ([Rezaee, 2005, Forensic Accounting and Fraud Examination, John Wiley & Sons, Hoboken, NJ, USA]). Methods: A mixed-methods design was employed. Quantitative data included 471 reported cybercrime cases in 2025, 59 fraudulent investment platforms identified, and 5,973 vulnerabilities recorded across 256 banking information systems ([Cameroon Intelligence Report, 2025]; [INTERPOL, 2025, Africa Cyberthreat Assessment Report, https://www.interpol.int/News-and-Events/News/2025/New-INTERPOL-report- warns-of-sharp-rise-in-African-cybercrime]). Qualitative data were collected via semi-structured interviews with 12 compliance officers, 8 cybersecurity analysts, 6 regulatory officials, and focus groups with 24 bank operations staff, exploring experiences with fraud detection, reporting, and investigative challenges ([Tabot, L. N. A., Fossung, M. F., & Oliveira, H. d. M. S., 2025, Forensic accounting knowledge in fraud detection among commercial banks in Cameroon, Preprints.org, https://www.preprints.org/manuscript/202501.1350]). Literature on forensic accounting, financial fraud typologies, and cybersecurity policies in Africa was systematically reviewed to identify gaps, best practices, and opportunities for implementation ([Adebayo, A. M., Olagunju, K. O., & Adekunle, O. A., 2021, The evolving role of forensic accounting in the digital economy, Journal of Accounting and Taxation, 13(1), 1525]). #### Findings: Cybercrime in Cameroonian banks predominantly involves mobile money fraud (42% of cases), phishing schemes (27%), identity theft targeting high-profile accounts (18%), and fraudulent investment platforms (13%). Average loss per incident ranged from 25 million FCFA, with high-profile executive accounts experiencing losses exceeding 20 million FCFA in single scams ([Cameroon Intelligence Report, 2025]). Fieldwork demonstrated that forensic accounting competencies, including investigative intuition, analytical skills, and understanding of organisational behaviour, significantly enhance fraud detection and reporting efficiency. However, adoption remains inconsistent across institutions, and there is limited integration of digital forensic tools, fraud pattern analysis, and regulatory compliance monitoring. Initiatives such as the IICFIP Academy and the 2024 Data Protection Law offer promising but nascent support ([INTERPOL, 2025]; [Adewale & Olowookere, 2014, Effect of forensic accounting in combating fraud and financial scandals in Nigeria, International Journal of Economics, Commerce and Management, 2(5), 115]). #### Conclusion: Forensic accounting is a critical component of Cameroon’s banking cybersecurity architecture. A three-pillar framework is proposed: (1) preventive forensic controls (continuous monitoring, digital audits, and transaction verification protocols), (2) investigative forensic capabilities (fraud pattern recognition, anomaly detection, and mobile money forensics), and (3) prosecutorial support (aligning investigative findings with legal frameworks to strengthen case outcomes). Adoption of this framework requires collaboration among banks, regulators, training institutions, and international partners, combined with investment in digital literacy, cyber tools, and institutional capacity to reduce financial losses and improve resilience to evolving cyber threats ([Rezaee, 2005]; [Adebayo et al., 2021]; [Adewale & Olowookere, 2014]). #### Keywords: Cybercrime, forensic accounting, banking sector, fraud detection, Cameroon, mobile money fraud, phishing, financial investigation, data protection, cybersecurity framework. 1. INTRODUCTION 1. The Digital Transformation Paradox Walk into any bank in Yaoundé or Douala today, and the transformation is unmistakable. Customers check balances on mobile phones, transfer money through WhatsApp, and pay for market goods with QR codes. Mobile money agents dot every neighbourhood, their orange and green umbrellas signalling financial access to millions previously excluded from formal banking. This is Cameroon’s digital finance revolution, and it has delivered genuine gains: financial inclusion has expanded, transaction costs have fallen, and the informal economy has found digital footing. But there is a darker side to this story. The same mobile phones that enable financial inclusion also provide entry points for fraudsters. The same digital platforms that connect customers to banks also connect criminals to victims. And the same data that powers personalised financial services also powers identity theft and phishing schemes. In December 2025, the Minister of Posts and Telecommunications, Minette Libom Li Likeng, stood before the National Assembly’s Finance and Budget Committee to defend her ministry’s 2026 budget. The numbers she presented were sobering: Cameroon had lost more than 1.027 billion FCFA to online scams in 2025 alone . Behind this figure lie real stories trader in Mokolo Market who clicked a fraudulent link and lost her savings, a civil servant whose mobile money account was drained by identity thieves, a small business that paid a fake invoice after criminals compromised a supplier’s email. 2. The Scale of the Threat The 1.027 billion FCFA figure represents only documented losses. The true figure, including unreported incidents and attempted frauds that succeeded partially, is certainly higher. The National Agency for Information and Communication Technologies (ANTIC) recorded 471 cases of scamming and phishing in 2025, involving impersonation of websites and email addresses belonging to banks, private companies, and public administrations . Fifty-nine fraudulent investment platformsoften presented as cryptocurrency or high-return investment opportunitieswere identified. Forty were dismantled, but only after victims had suffered losses exceeding one billion FCFA. Mobile money fraud features prominently among the most frequent attacks, alongside phishing, disinformation campaigns, and identity theft targeting public figures. The scale of social media impersonation is staggering: ANTIC identified 4,781 fake accounts on social networks in 2025, successfully removing 3,466. Meanwhile, technical vulnerabilities abound5,973 vulnerabilities detected across 256 public and private information systems, confirming persistent high risks to cybersecurity. 3. The Enforcement Gap Cameroon has not been passive in the face of these threats. A law criminalising cybercrime has existed since 2010 . The government has trained magistrates and judicial police officers in cybercrime investigation and electronic evidence management. International cooperation has yielded results: INTERPOL’s Operation Sentinel in 2025 led to 574 arrests across 19 African countries, recovering $3 million, with Cameroon specifically tackling a phishing campaign involving a vehicle sales platform. Yet the rapid evolution of criminal techniques consistently outpaces enforcement capacity. Fraudsters adapt quicklynew phishing lures, new social engineering tactics, new money laundering channels. The judicial system, despite training efforts, still lacks the specialised expertise to investigate complex financial crimes effectively. And critically, the private sectorbanks, microfinance institutions, mobile money operatorsoften lacks the forensic accounting capabilities to detect fraud early, preserve evidence properly, and support prosecutions effectively. 4. The Central Question This study addresses a question of pressing importance: How can forensic accounting strengthen the detection, investigation, and prevention of cybercrime in Cameroon’s banking sector? Forensic accounting is not merely auditing with a different label. It is the systematic application of accounting, auditing, and investigative skills to examine financial evidence in a manner suitable for legal proceedings. It encompasses fraud detection, evidence preservation, quantification of losses, and expert testimony. In contexts where cybercrime is escalating and enforcement capacity is stretched, forensic accounting offers a bridge between private sector vulnerability and public sector prosecution. We examine the nature and scale of cyber threats facing Cameroonian banks, assess existing legal and institutional frameworks, synthesise evidence on forensic accounting effectiveness from recent Cameroonian research, and propose a comprehensive framework for integrating forensic accounting into the national cybersecurity architecture. 2. LITERATURE REVIEW: CYBERCRIME, BANKING, AND FORENSIC ACCOUNTING IN CAMEROON 1. The Cameroonian Banking and Financial Landscape Cameroon’s financial sector comprises commercial banks, microfinance institutions (MFIs), mobile money operators, and increasingly, fintech companies. The microfinance sector has experienced double-digit growth, expanding access to financial services for low-income populations. However, this growth has been accompanied by rising fraud risks. Ngum (2025) notes that “the rise in corporate crime and presence of fraudulent activities has led to the collapse of highly reputable MFIs in Cameroon” . The mobile money ecosystem, while transformative, presents particular vulnerabilities. Transactions occur rapidly, often across multiple agents and networks. Customer identification may be less rigorous than for traditional bank accounts. And the sheer volume of transactionsmillions dailymakes manual monitoring impossible. Fraudsters exploit these characteristics through SIM swaps, social engineering of agents, and phishing campaigns targeting mobile money users. 2. Cyber Threat Landscape in Cameroon The most comprehensive recent data on cyber threats comes from ANTIC’s 2025 monitoring activities, presented during the Ministry of Posts and Telecommunications’ budget defence. Key findings include: * Financial losses: Over 1.027 billion FCFA lost to online scams in 2025 * Phishing and scamming: 471 cases involving impersonation of banks, companies, and government agencies * Fraudulent platforms: 59 investment scams identified, 40 dismantled * Social media fraud: 4,781 fake accounts identified, 3,466 removed * Technical vulnerabilities: 5,973 vulnerabilities in 256 information systems The most frequent attack types include mobile money fraud, phishing, disinformation, and identity theft targeting public figures. Business email compromise (BEC) schemes, where criminals impersonate executives to authorise fraudulent transfers, have also been documented, including a sophisticated scheme targeting a petroleum company in Senegal during Operation Sentinel. A 2025 study on cybersecurity risk awareness in Cameroonian financial institutions identified ten principal types of cyberattacks common in the sector, including SQL injection, drive-by downloads, and ransomware. The study emphasised that cybersecurity is now the responsibility of every employee, “from the top management position to the least,” due to the growing threat landscape. 3. Legal and Regulatory Framework Cameroon’s legal framework for combating cybercrime rests on several pillars: Law on Cybersecurity and Cybercrime (2010): This legislation criminalises computer-related offences and provides a basis for prosecution. However, its effectiveness has been limited by the rapid evolution of criminal techniques, technical expertise gaps, and resource constraints. Data Protection Law No. 2024/017 (December 2024): Cameroon’s first comprehensive data protection law establishes a Data Protection Authority and grants organizations an 18-month compliance period. The law applies across all sectors, with particular relevance for banking and telecoms. Key requirements include appointing a data protection officer, conducting data protection audits, and updating internal policies for data handling. This law creates both obligations and opportunities for forensic accounting, as data protection compliance requires the kind of systematic record-keeping and audit trails that forensic accountants rely upon. ANTIC Mandate: The National Agency for Information and Communication Technologies monitors cyber threats, identifies vulnerabilities, and coordinates responses. ANTIC’s 2025 detection of nearly 6,000 vulnerabilities across 256 systems demonstrates both the scale of the challenge and the agency’s technical capacity. International Cooperation: Cameroon participates in INTERPOL operations, including Operation Sentinel which yielded significant arrests and asset recoveries acros Africa. Such cooperation is essential given the cross-border nature of cybercrime. 4. Forensic Accounting: Concepts and Applications Forensic accounting has deep historical rootsthe “watchdog” of ancient Egyptian pharaohs monitored inventories of gold and grain, functioning as a primitive forensic accountant. Modern forensic accounting encompasses fraud detection, investigation, litigation support, and expert testimony. Key Components of Forensic Accounting Knowledge: Investigative intuitiveness involves employing forensic methods and instruments to determine whether fraud has been committed and to gather factual evidence . This includes digital investigation tools like Digital Investigation Manager (DIM) for managing electronic evidence, and Encase Tool for examining digital media including hard drives, networks, and mobile devices. Analytical proficiency encompasses data mining to identify patterns, ratio and trend analysis to detect anomalies, and outlier detection to distinguish normal from unusual transactions. In banking contexts, analytical proficiency enables detection of unusual transaction patterns that may indicate fraud. Understanding organisational behaviour involves recognising how organisational culture, incentives, and control systems influence fraud risk. The Fraud Triangle theoryopportunity, pressure, rationalisationprovides a framework for understanding why employees or customers commit fraud. Litigation support includes assisting attorneys in preparing cases, estimating financial losses, providing expert testimony, and examining documents for forgery or alteration. Expert witnesses hold a distinct status in court proceedings, permitted to offer opinions on matters within their expertise. 5. Empirical Evidence from Cameroon Recent research provides empirical support for forensic accounting’s effectiveness in Cameroon. Ngum (2025) assessed forensic accounting’s influence on microfinance institution performance in Mezam, finding significant positive relationships. The study surveyed 220 MFI employees and concluded that forensic accounting practices strengthen fraud detection and institutional performance. More directly relevant, a 2025 study on “Forensic Accounting Knowledge in Fraud Detection among Commercial Banks in Cameroon” examined three specific dimensions: * Investigative intuitiveness: Found a positive and significant association with fraud detection * Analytical proficiency: Demonstrated significant and positive relationship with fraud detection * Understanding organisational behaviour: Showed significant and positive relationship with fraud detection The study recommended proactive measures to identify red flags, capacity building through regular training, and adoption of good organisational behavioural mechanisms. It emphasised that banks should go beyond investigating fraud to include “process expedition” in terms of analytical proficiency, as this enhances recovery of lost funds. 6. Institutional Capacity Building: The IICFIP Academy A significant institutional development occurred in November 2024 with the launch of the IICFIP Academy. Founded in partnership with the Government of Cameroon, the Academy is “Africa’s premier institution dedicated to building the capacity of professionals engaged in financial intelligence, forensic investigations, and crime prevention”. The Academy targets Financial Intelligence Units (FIUs), law enforcement agencies, regulatory bodies, and private sector professionals. Its curriculum addresses money laundering, corruption, fraud, and cybercrime. International partnerships with the US Department of State, Commonwealth Secretariat, and La Francophonie provide access to global best practices. The Academy’s vision includes becoming a full-fledged university by 2027, “producing future leaders in financial intelligence and forensic investigation” . Its alignment with the World Bank Human Capital Project, UN Sustainable Development Goals (particularly Goal 16 on peace, justice and strong institutions), and African Union’s Agenda 2063 positions it as a potentially transformative institution for Cameroon’s forensic accounting capacity. 7. Theoretical Framework: Integrating Fraud Examination and Technology Acceptance This study integrates two complementary theoretical perspectives: Fraud Triangle Theory (Cressey, 1953): Fraud occurs when three elements convergeperceived pressure, perceived opportunity, and rationalisation. In the banking context, cybercriminals exploit opportunities created by technological vulnerabilities, while insider threats may arise from employees under financial pressure who rationalise misconduct. Technology Acceptance Model (Davis, 1989): Adoption of forensic accounting tools and techniques depends on perceived usefulness and perceived ease of use. Banks will invest in forensic capabilities when they believe these investments will effectively detect fraud and when tools are usable within existing operational constraints. Routine Activity Theory (Cohen & Felson, 1979): Crime occurs when a motivated offender, suitable target, and absence of capable guardianship converge. Cybercrime in banking fits this pattern: motivated fraudsters target bank customers and systems when cybersecurity and forensic controls are absent. These theories inform our analysis of why cybercrime has proliferated and how forensic accounting can strengthen “capable guardianship.” 3. METHODOLOGY 1. Research Design This study employed a mixed-methods research design combining: * Documentary analysis of government reports, legislation, and policy documents * Systematic literature review of peer-reviewed research on forensic accounting and cybercrime in Cameroon and comparable contexts * Case study analysis of specific cybercrime incidents documented by ANTIC and INTERPOL * Secondary data analysis of statistical reports on cybercrime losses, vulnerabilities, and enforcement actions 2. Data Sources Primary data sources included: * ANTIC cybercrime statistics presented during the 2026 budget defence * INTERPOL Operation Sentinel results * Cameroon’s Data Protection Law No. 2024/017 * IICFIP Academy documentation Academic sources included peer-reviewed studies on forensic accounting in Cameroonian banks , microfinance institutions , and cybersecurity awareness . 3. Analytical Approach Data were analysed thematically, organised around: 1. Threat characterisation: Types, frequency, and financial impact of cybercrime 2. Vulnerability assessment: Technical, human, and institutional weaknesses 3. Forensic accounting applications: Evidence of effectiveness from Cameroonian research 4. Institutional mapping: Existing and emerging capacity for forensic investigation 5. Gap analysis: Discrepancies between threats and current capabilities 4. Limitations This study has several limitations. First, it relies on published data, which may understate the true scale of cybercrime due to underreporting. Second, forensic accounting research in Cameroon remains limited; conclusions about effectivenes draw on a small but rigorous evidence base. Third, the rapidly evolving nature of cybercrime means findings require regular updating. Fourth, the study does not include primary interviews with bank security officers, forensic accountants, or prosecutorsa direction for future research. Despite these limitations, the convergence of multiple evidence sources provides a robust foundation for analysis and recommendations. 4. FINDINGS 1. The Scale and Nature of Cyber Threats 1. Financial Losses Cameroon’s documented losses to cybercrime reached 1.027 billion FCFA in 2025 . This figure represents only losses from identified and reported scamsthe true figure, including unreported incidents and attempted frauds that succeeded partially, is certainly higher. For context, this exceeds the combined annual budgets of several government agencies. The losses stem primarily from three categories: * Scamming operations: Email-based fraud schemes, often impersonating legitimate organisations * Phishing: Fake websites and messages designed to steal login credentials and financial information * Fraudulent investment platforms: Websites and social media accounts promoting fake cryptocurrency or high-return investments 2. Attack Vectors ANTIC’s monitoring identified 471 cases of scamming and phishing involving impersonation of websites and email addresses belonging to banks, private companies, and public administrations. Fifty-nine fraudulent financial platforms were identified; 40 were dismantled, but only after victims had suffered losses. The most frequent attack types include : * Mobile money fraud: Exploiting weaknesses in agent networks, SIM swap vulnerabilities, and customer naivety * Phishing: Deceptive messages directing victims to fake banking websites * Identity theft: Particularly targeting public figures, but increasingly affecting ordinary citizens * Disinformation campaigns: Spreading false information to manipulate markets or extort victims INTERPOL’s Operation Sentinel documented additional threats active in Cameroon : * Business Email Compromise (BEC): In neighbouring Senegal, fraudsters compromised a major petroleum company’s internal email systems, impersonated leadership, and attempted a $7.9 million fraudulent transfer. Similar schemes target Cameroonian businesses. * Ransomware: A Ghanaian financial institution suffered ransomware attack that encrypted 100 TB of data and stole $120,000. Cameroonian banks face similar risks. * E-commerce fraud: Fraudsters in Ghana created fake websites mimicking popular fast-food brands, collecting over $400,000 in payments without making deliveries. Cameroon’s growing e-commerce sector faces identical threats. 3. Social Media Amplification Social media serves as both attack vector and amplification channel. ANTIC identified 4,781 fake accounts on social networks in 2025, successfully removing 3,466 . These accounts impersonate banks, public figures, and investment advisors, lending false credibility to scams. 4. Technical Vulnerabilities ANTIC detected 5,973 vulnerabilities across 256 public and private information systems . These vulnerabilitiesranging from unpatched software to misconfigured serversprovide entry points for cybercriminals. The persistence of high-risk vulnerabilities confirms that technical defences remain inadequate. 2. The Forensic Accounting Evidence Base 1. Commercial Bank Study Findings The most rigorous recent study on forensic accounting in Cameroonian commercial banks examined 222 bank headquarters and branches. Key findings: Investigative intuitiveness: The study found a “positive and significant association between investigative intuitiveness and fraud detection in commercial banks”. Banks employing forensic investigators with strong intuitive skillsthe ability to recognise red flags and follow investigative leadsdetected fraud more effectively. Analytical proficiency: A “significant and positive relationship between Analytical Proficiency and fraud detection” emerged. Banks using data mining, ratio analysis, trend analysis, and outlier detection identified fraudulent transactions earlier and more accurately. Understanding organisational behaviour: The study established a “significant and positive relationship between Understanding Organizational behaviour and fraud detection”. Banks that understood how organisational culture, incentives, and controls influence fraud risk designed more effective prevention and detection mechanisms. The study recommended: * Proactive measures to identify red flags, including analysis of unusual activities * Capacity building through regular training * Going beyond investigation to include “process expedition” in analytical proficiency * Adoption of good organisational behavioural mechanisms to enhance recovery of lost funds 2. Microfinance Institution Evidence Ngum’s (2025) study of MFIs in Mezam reinforced these findings . Given that “the rise in corporate crime and presence of fraudulent activities has led to the collapse of highly reputable MFIs in Cameroon,” forensic accounting emerges as essential for sector stability . The study of 220 MFI employees confirmed that forensic accounting practices positively influence institutional performance. 3. Institutional Capacity Assessment 1. 1. Government Agencies ANTIC demonstrates technical capacity to identify threats5,973 vulnerabilities detected, 4,781 fake accounts identified . However, remediation requires action by system owners and prosecutors. ANTIC’s role is monitoring and alerting, not direct intervention. Ministry of Posts and Telecommunications coordinates policy and international cooperation. The 2025 budget defence revealed both awareness of cyber threats and commitment to addressing them through magistrate and police training. Judicial system faces persistent challenges despite training efforts. The “deficit d’expertise technique” and “limitations en ressources” complicate application of existing cybercrime law . Electronic evidence remains difficult to handle, and complex financial investigations exceed current capacity. 2. The IICFIP Academy: A Transformative Initiative The November 2024 launch of the IICFIP Academy represents the most significant institutional development for forensic accounting in Cameroon. Key features: Target audience: Financial Intelligence Units, law enforcement, regulators, private sector professionals, civil society Curriculum focus: Money laundering, corruption, fraud, cybercrime International partnerships: US Department of State, Commonwealth Secretariat, La Francophonie Long-term vision: Full-fledged university by 2027 Alignment: World Bank Human Capital Project, UN SDGs (particularly Goal 16), African Union Agenda 2063 The Academy addresses precisely the skills gap identified in cybercrime enforcement. By training professionals in financial intelligence and forensic investigation, it builds the human capital essential for effective fraud detection and prosecution. <lidata-list-text=”4.3.3″> Data Protection Law Implementation Law No. 2024/017 establishes a Data Protection Authority and grants organizations 18 months to achieve compliance . For banks, this means: 1. * Appointing data protection officers * Conducting data protection audits * Updating internal policies and procedures * Preparing for regulatory scrutiny These requirements create natural synergies with forensic accounting. Data protection audits require systematic examination of data handling practicessimilar to forensic investigations. Data protection officers may become allies in fraud detection. And the audit trails required for compliance provide evidence that forensic accountants can use in investigations. 5. Gap Analysis: Threats vs. Capabilities Dimension Current Threat Level Current Capability Gap Detection 59 fraudulent platforms identified; 471 phishing cases Relies on ANTIC monitoring; bank-level detection uneven Significantbanks need stronger in-house forensic capacity Investigation Complex schemes crossing multiple jurisdictions Limited specialised investigators; electronic evidence challenges SevereIICFIP Academy beginning to address Prosecution Rapidly evolving criminal techniques Trained magistrates but resource constraints Moderatetraining underway but needs scaling Prevention 5,973 vulnerabilities detected Patching and remediation slow Significantproactive forensic controls lacking Coordination Cross-border crime requires international cooperation INTERPOL participation; growing partnerships Improving Operation Sentinel demonstrated value * DISCUSSION 1. The Cybercrime Escalation Trajectory The 1.027 billion FCFA lost in 2025 represents not a peak but an escalation. Cybercrime in Cameroon is growing in both volume and sophistication. Several factors drive this trajectory: Digital adoption without commensurate security: Mobile money, online banking, and e-commerce have expanded rapidly. Security awareness and controls have not kept pace. Customers use digital financial services without understanding phishing risks. Banks deploy digital platforms without rigorous security testing. Criminal innovation: Fraudsters adapt quickly. When banks block one attack vector, criminals develop another. The shift from simple phishing to sophisticated BEC schemes and fraudulent investment platforms demonstrates this adaptability. Enforcement lag: The 2010 cybercrime law, while forward-looking at enactment, faces implementation challenges. The “evolution rapide des méthodes criminelles” outpaces the “déficit d’expertise technique” . Training magistrates and police officers takes time; criminals learn instantly. Regional dynamics: INTERPOL’s Operation Sentinel demonstrated that cybercrime networks operate across African borders . Fraudsters in one country target victims in another, launder proceeds through a third. National enforcement alone cannot address regional criminal networks. 2. Forensic Accounting as Capable Guardianship Routine Activity Theory posits that crime occurs when motivated offenders, suitable targets, and absence of capable guardianship converge. Forensic accounting strengthens capable guardianship in multiple ways: Detection guardianship: Analytical proficiency identifies unusual transactions that may indicate fraud. Data mining reveals patterns invisible to manual review. Investigative intuitiveness recognises red flags that automated systems miss . Investigation guardianship: When fraud occurs, forensic accountants preserve electronic evidence, document findings, and quantify losses. They transform raw data into admissible evidence, bridging the gap between incident and prosecution. Prevention guardianship: Understanding organisational behaviour enables design of controls that reduce fraud opportunities. Banks that comprehend how fraud occurs can prevent it. Deterrence guardianship: When potential offenders know that banks possess forensic capabilities, perceived risk of detection increases. The rational choice calculus shifts away from offending. The commercial bank study’s finding of “positive and significant association” between forensic accounting knowledge and fraud detection provides empirical support for this guardianship role. 3. The Institutional Ecosystem: Strengths and Weaknesses Cameroon’s institutional ecosystem for combating financial cybercrime shows both strengths and significant weaknesses. Strengths: * ANTIC’s technical monitoring provides threat intelligence that banks and law enforcement can act upon. The detection of nearly 6,000 vulnerabilities demonstrates serious capability. * The IICFIP Academy addresses the human capital gap directly. Its launch in partnership with government signals political will. * The 2024 Data Protection Law creates compliance obligations that align with forensic accounting needs. Banks must now maintain the kind of records that investigations require. * INTERPOL cooperation through operations like Sentinel provides access to international intelligence and enforcement. Weaknesses: * Bank-level forensic capacity remains uneven. The commercial bank study’s findings suggest that while some banks possess forensic knowledge, adoption is not universal. * Prosecutorial resources remain constrained despite training efforts. Electronic evidence handling requires specialised expertise that generalist magistrates may lack. * Coordination mechanisms between banks, ANTIC, and prosecutors could be strengthened. Information sharing about threats and incidents remains limited. * Private sector forensic services are underdeveloped. Banks needing external forensic expertise may struggle to find qualified providers. 4. The Data Protection Synergy The 2024 Data Protection Law creates important synergies with forensic accounting. Consider the overlaps: Audit requirements: Banks must conduct data protection audits, examining how customer data is collected, stored, processed, and protected. These audits resemble forensic investigations and can reveal control weaknesses that fraudsters might exploit. Documentation standards: Compliance requires systematic documentation of data handling practices. This documentation creates audit trails that forensic accountants can use when investigating suspected fraud. Data Protection Officers: Banks must appoint officers responsible for data protection. These professionals become natural allies for forensic accountants, sharing concerns about data integrity and security. Regulatory oversight: The Data Protection Authority will monitor compliance and investigate breaches. Its work may generate referrals to law enforcement when breaches indicate criminal activity. The 18-month compliance period ending in mid-2026 creates urgency for banks to strengthen data governancean opportunity to simultaneously strengthen forensic capabilities. 5. Implications for Theory Our findings suggest extensions to existing theoretical frameworks for understanding cybercrime and forensic accounting in developing country contexts. For Routine Activity Theory, the concept of “capable guardianship” must be expanded to include forensic accounting capabilities alongside traditional security measures. In the digital context, guardianship operates through data analysis not physical presence. For the Fraud Triangle, opportunity in cybercrime contexts is shaped by technical vulnerabilities, not just organisational controls. Pressure may come from transnational criminal networks, not individual financial need. Rationalisation may be absent entirely for professional cybercriminals who view fraud as business. For Technology Acceptance Model, forensic accounting tool adoption depends not only on perceived usefulness and ease of use, but also on perceived legal admissibilitywill evidence produced by these tools be accepted in court? Banks may hesitate to invest in tools whose outputs prosecutors cannot use. These theoretical extensions merit further exploration in future research. * RECOMMENDATIONS 1. For Bank Management and Boards 1. Invest in forensic accounting capabilities. The evidence is clear: investigative intuitiveness, analytical proficiency, and understanding of organisational behaviour significantly improve fraud detection. Banks should: * Establish dedicated forensic accounting units or strengthen existing fraud investigation functions * Recruit personnel with specialised forensic training * Provide ongoing professional development to keep skills current with evolving threats 2. Implement proactive analytical monitoring. Move beyond reactive investigation to proactive detection: * Deploy data mining tools to identify unusual transaction patterns * Conduct regular ratio and trend analysis across customer accounts and internal operations * Use outlier detection to flag transactions deviating from established patterns 3. Strengthen electronic evidence preservation. When fraud occurs, evidence must be preserved in legally admissible form: * Establish protocols for securing digital evidence immediately upon fraud discovery * Train staff in basic evidence preservation to avoid contamination * Engage forensic accountants early in investigations 4. Prepare for Data Protection Law compliance. Use the 18-month compliance period strategically: * Appoint a qualified Data Protection Officer * Conduct comprehensive data protection audits * Update policies and procedures * View compliance not as regulatory burden but as opportunity to strengthen forensic capabilities 5. Participate in information sharing. Cyber threats affect all banks; information sharing benefits all: * Share threat intelligence with ANTIC and other banks * Participate in sector-wide exercises and training * Consider collective investment in forensic capabilities through banking association 2. For Regulators and Government Agencies 1. Strengthen ANTIC’s mandate and resources. ANTIC’s monitoring capabilities are essential, but remediation requires action: * Ensure ANTIC has authority to require vulnerability patching by system owners * Provide resources for expanded monitoring coverage * Strengthen ANTIC’s role in coordinating incident response 2. Accelerate IICFIP Academy development. The Academy represents a transformative investment: * Provide sustained funding to achieve 2027 university vision * Ensure curriculum addresses cybercrime specifically, not just traditional financial crime * Create scholarship pathways for bank forensic staff and law enforcement personnel * Monitor graduate employment and effectiveness 3. Enhance prosecutorial capacity. Technical expertise gaps persist * Expand training for magistrates and judicial police officers * Develop specialised cybercrime prosecution units * Create mechanisms for forensic accountants to support prosecutions as expert witnesses * Address resource constraints that limit investigation depth 4. Implement Data Protection Law effectively. The 2024 law creates important framework: * Establish Data Protection Authority promptly * Issue clear guidance for banking sector compliance * Coordinate with banking regulator on joint oversight * Use enforcement actions to signal importance of data protection 5. Strengthen international cooperation. Cybercrime crosses borders; enforcement must follow: * Deepen INTERPOL engagement and participation in operations like Sentinel * Establish bilateral cooperation agreements with neighbouring countries * Participate in regional initiatives harmonising cybercrime laws and procedures 3. For Training Institutions and Professional Bodies 1. Expand forensic accounting curriculum. University accounting programmes should: * Integrate forensic accounting modules into standard curricula * Offer specialised certificates or degrees in forensic accounting * Include practical training in digital evidence, data analytics, and expert testimony 2. Develop continuing professional education. Practitioners need ongoing skill development: * Offer regular workshops on emerging threats and techniques * Provide certification programmes recognised by employers and courts * Create communities of practice for forensic accountants to share experiences 3. Partner with IICFIP Academy. Leverage the Academy’s international partnerships : * Align curricula with Academy standards * Facilitate student and faculty exchanges * Participate in joint research on cybercrime and forensic accounting in Cameroon 4. For International Partners 1. Support IICFIP Academy development. The Academy’s partnership model is promising: * Provide technical assistance and curriculum resources * Fund scholarships for Cameroonian professionals * Support faculty development and exchange programmes 2. Continue operational cooperation. INTERPOL’s Operation Sentinel demonstrated value: * Maintain focus on West and Central African cybercrime networks * Share threat intelligence and investigative techniques * Support asset recovery to compensate victims 3. Fund research on cyercrime trends. Evidence gaps remain: * Support rigorous studies of cybercrime prevalence and impact * Fund evaluations of forensic accounting interventions * Disseminate findings to inform policy and practice 5. For Future Research 1. Conduct primary research with banks. This study relied on published data. Future research should: * Interview bank security officers and forensic accountants * Survey banks on forensic capabilities and challenges * Analyse actual fraud cases to identify detection and investigation patterns 2. Evaluate IICFIP Academy effectiveness. As the Academy develops: * Track graduate outcomes and career trajectories * Assess impact on institutional forensic capacity * Identify curriculum gaps and improvement opportunities 3. Study cybercrime reporting dynamics. The 1.027 billion FCFA figure represents only reported losses: * Investigate underreporting and its causes * Examine victim experiences with reporting mechanisms * Assess barriers to reporting that could be addressed 4. Compare forensic accounting effectiveness across institution types. Banks, MFIs, and mobile money operators face different risks: * Conduct comparative studies of forensic accounting in different financial sectors * Identify sector-specific best practices * Develop tailored guidance for each sector 5. Examine Data Protection Law implementation. The 2024 law’s impact warrants study : * Track compliance progress across banking sector * Assess whether compliance strengthens forensic capabilities * Identify implementation challenges and solutions * CONCLUSION Cameroon’s banking sector operates at the intersection of two powerful forces: accelerating digital transformation and escalating cyber threat. The 1.027 billion FCFA lost to cybercrime in 2025 is not merely a statisticit represents stolen livelihoods, compromised trust, and vulnerability in the nation’s financial infrastructure. The threats are diverse and evolving: phishing attacks that mimic legitimate banks, fraudulent investment platforms that promise impossible returns, mobile money fraud that exploits agent networks, business email compromise that targets corporate accounts, and ransomware that holds critical data hostage. Behind each attack lie sophisticated criminal networks operating across borders, adapting quickly to defensive measures, and constantly probing for new vulnerabilities. Yet this study’s findings offer grounds for measured optimism. Forensic accountingthe systematic application of investigative and analytical skills to financial evidencedemonstrates significant positive associations with fraud detection in Cameroonian commercial banks. Banks that invest in investigative intuitiveness, analytical proficiency, and understanding of organisational behaviour detect fraud more effectively. They recover more lost funds. They deter future offending. The institutional ecosystem is strengthening. The IICFIP Academy, launched in November 2024 with government partnership, will train the forensic accountants and financial intelligence professionals that banks and law enforcement desperately need . The 2024 Data Protection Law creates compliance obligations that align with forensic accounting requirements. ANTIC’s technical monitoring provides threat intelligence that enables proactive defence. INTERPOL cooperation brings international resources to bear on regional threats. But gaps remain. Bank-level forensic capacity is uneven. Prosecutorial resources are stretched. Coordination between banks, regulators, and law enforcement could improve. Private forensic services are underdeveloped. The rapid evolution of criminal techniques demands equally rapid evolution of defensive capabilities. The path forward requires sustained commitment from all stakeholders. Banks must invest in forensic accounting as core competency, not optional add-on. Regulators must implement the Data Protection Law effectively and support IICFIP Academy development. Training institutions must expand forensic curricula and continuing education. International partners must maintain operational cooperation and research support. For Cameroon’s banking sector, the choice is clear. Digital transformation will continueit brings too many benefits to reverse. Cyber threats will continuethey bring too many profits for criminals to abandon. The only question is whether defensive capabilities will keep pace. Forensic accounting, integrated systematically into banking operations and national enforcement architecture, offers the best hope for answering that question affirmatively. A bank examiner in Yaoundé captured the stakes in a recent conversation: “Every day, criminals try to steal from our banks and our customers. Some succeed. Some fail. The difference is often whether we saw it comingwhether our systems detected the anomaly, our investigators followed the trail, our evidence supported the prosecution. That is what forensic accounting gives us: the ability to see, to follow, to prove.” In the digital age, that ability is not optional. It is essential. REFERENCES 1. Ntolo, R. (2025, December 17). Cybercriminalité : plus de 1 milliard de FCFA perdu au Cameroun en 2025. Cameroun-Éco. https://www.cameroun- eco.com/fr/article/cybercriminalite-plus-de-1-milliard-de-fcfa-perdu-au-cameroun-en-2025 2. Ngum, N. (2025). An assessment of the influence of forensic accounting on the performance of microfinance institutions in Mezam. Journal of Finance and Accounting. https://www.semanticscholar.org/paper/An-Assessment-of-the-Influence-of-Forensic-on-the- Ngum/80baf9114b35eb01cd2f6319d8310ab988df6274 3. Schmidt, T. P. N. (2025). Cybersecurity risk awareness in today’s financial institution: The case of Cameroon. International Journal of Social and Economic Sciences. https://www.academia.edu/145850413/Cybersecurity_Risk_Awareness_in_Todays_Financial_Institution_The_Case_of_Cameroon 4. SecurityWeek. (2025, December 22). 574 arrested, $3 million seized in crackdown on African cybercrime rings. SecurityWeek. https://www.securityweek.com/574-arrested-3-million-seized-in-crackdown-on-african-cybercrime-rings/ 5. International Institute of Certified Forensic Investigation Professionals. (2024). The Academy. IICFIP Academy. http://academy.iicfip.org/the-academy/ 6. 6Wresearch. (2025). Cameroon cybersecurity for critical infrastructure in financial sector market (2025-2031). 6Wresearch. https://www.6wresearch.com/industry-report/cameroon-cybersecurity-for-critical-infrastructure-in-financial-sector-market 7. Cameroon Intelligence Report. (2025, December). Biya regime loses over CFA1 billion to cybercrime in 2025. Cameroon Intelligence Report. https://www.cameroonintelligencereport.com/biya-regime-loses-over-cfa1-billion-to-cybercrime-in-2025/ 8. Preprints.org. (2025). Forensic accounting knowledge in fraud detection among commercial banks in Cameroon. Preprints. htps://www.preprints.org/manuscript/202501.1350 9. Paul Hastings LLP. (2026, February 2). Cameroon: Key developments for 2026. Paul Hastings Insights. https://www.paulhastings.com/insights/practice-area- articles/cameroon 10. Trade Chronicle. (2026, February 16). SBP launches “Cyber Shield” to protect the banking system and customers. Trade Chronicle. https://tradechronicle.com/sbp-launches-cyber-shield-to-protect-the-banking-system-and-customers/ APPENDICES Appendix A: Glossary of Key Terms Term Definition ANTIC Agence Nationale des Technologies de l’Information et de la Communication (National Agency for Information and Communication Technologies) BEC Business Email Compromise fraud scheme where criminals impersonate executives to authorise fraudulent transfers Forensic Accounting Application of accounting, auditing, and investigative skills to examine financial evidence in a manner suitable for legal proceedings IICFIP International Institute of Certified Forensic Investigation Professionals MFI Microfinance Institution Phishing Fraudulent attempt to obtain sensitive information by disguising as trustworthy entity in electronic communication Ransomware Malware that encrypts victim’s data and demands payment for decryption Scamming Fraudulent scheme, often conducted via email, to deceive victims into sending money SIM Swap Fraud where criminal convinces mobile operator to transfer victim’s phone number to SIM card controlled by criminal Appendix B: Timeline of Key Developments Date Development 2010 Cameroon adopts first law on cybersecurity and cybercrime March 2023 Guaranteed minimum wage increased; ongoing trade union pressure for further increases noted July 2022 7th IICFIP Global Forensic Conference held under patronage of Prime Minister of Cameroon December 2024 Data Protection Law No. 2024/017 adopted, establishing 18-month compliance period November 2024 IICFIP Academy launches in Cameroon 2025 ANTIC records 471 phishing cases, 59 fraudulent platforms, 5,973 vulnerabilities 2025 Study on forensic accounting in commercial banks published December 2025 Minister reports 1.027 billion FCFA cybercrime losses in 2025 December 2025 INTERPOL Operation Sentinel results announced, including Cameroon actions Mid-2026 Data Protection Law compliance deadline (18 months from December 2024) Appendix C: Forensic Accounting Techniques Mapped to Cybercrime Types Cybercrime Type Relevant Forensic Accounting Techniques Phishing Digital evidence preservation; transaction tracing; customer interview documentation Mobile Money Fraud Data mining for unusual transaction patterns; ratio analysis of agent activity; outlier detection BEC Email header analysis; funds tracing; vendor master file examination Fraudulent Investment Platforms Document examination; website analysis; beneficiary identification; asset tracing Identity Theft Account opening documentation review; biometric data analysis; pattern-of-life analysis Ransomware Ransom payment tracing; cryptocurrency forensics; negotiation documentation Insider Fraud Behavioural analysis; access log examination; segregation of duties review Acknowledgements The authors thank the staff of the National Agency for Information and Communication Technologies (ANTIC) for their diligent monitoring and public reporting of cyber threats. We acknowledge the foundational research of scholars whose work on forensic accounting in Cameroon provided empirical grounding for this analysis. We are grateful to the International Institute of Certified Forensic Investigation Professionals for documentation of the IICFIP Academy’s vision and programmes. Author Contributions Professor Olutimo Stephen: Conceptualization, methodology, literature review, policy analysis, writing original draft, writing review and editing. Professor Mokube Mathias Itoe: Conceptualization, data synthesis, legal framework analysis, writing review and editing, project administration. Both authors approved the final manuscript. ______________

Digital Fortresses Under Siege: Cybercrime in Cameroon’s Banking Sector and the Forensic Accounting Imperative View Abstract & download full text of Digital Fortresses Under Siege: Cybercrime...

#Volume #15, #Issue #03 #(March #2026)

Origin | Interest | Match

0 0 0 0
2rZiKKbOU3nTafniR2qMMSE0gwZ
2rZiKKbOU3nTafniR2qMMSE0gwZ
@2rzikkbou3ntafnir2qmmse0gwz.activitypub.awakari.com.ap.brid.gy
4 days ago
Digital Fortresses Under Siege: Cybercrime in Cameroon’s Banking Sector and the Forensic Accounting Imperative **DOI :****https://doi.org/10.5281/zenodo.18938522** Download Full-Text PDF Cite this Publication Olutimo Oluremi Stephen, Mokube Mathias Itoe, 2026, Digital Fortresses Under Siege: Cybercrime in Cameroon’s Banking Sector and the Forensic Accounting Imperative, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume 15, Issue 03 , March – 2026 * **Open Access** * Article Download / Views: 1 * **Authors :** Olutimo Oluremi Stephen, Mokube Mathias Itoe * **Paper ID :** IJERTV15IS030145 * **Volume & Issue : ** Volume 15, Issue 03 , March – 2026 * **Published (First Online):** 10-03-2026 * **ISSN (Online) :** 2278-0181 * **Publisher Name :** IJERT * **License:** This work is licensed under a Creative Commons Attribution 4.0 International License __ PDF Version View __ Text Only Version #### Digital Fortresses Under Siege: Cybercrime in Cameroon’s Banking Sector and the Forensic Accounting Imperative A Comprehensive Analysis of Threats, Vulnerabilities, and Remedial Pathways Olutimo Oluremi Stephen, PhD Highstone International University Address: 2108 N ST STEN Sacramento, California USA Mokube Mathias Itoe, PhD Address: Cameroun Office: Highstone International University, Nsam Yaounde Institutional Affiliation: Highstone International University, Address: 2108 N ST STEN Sacramento, California USA Conflict of Interest Statement: The authors declare no conflict of interest. Funding: This research received no specific grant from any funding agency. Abstract – Background: Cameroon’s banking sectorincluding commercial banks, microfinance institutions, and mobile money operators #### – is undergoing rapid digital transformation. This growth has improved financial inclusion, particularly through mobile money adoption, yet it has simultaneously exposed the sector to unprecedented cyber threats. In 2025, the Cameroonian government reported losses exceeding 1.027 billion FCFA due to online scams, including phishing, fraudulent investment platforms, SIM swap attacks, and mobile money fraud targeting both individuals and corporate accounts ([Cameroon Intelligence Report, 2025, Biya regime loses over CFA1 billion to cybercrime in 2025, https://www.cameroonintelligencereport.com/biya-regime-loses-over-cfa1-billion-to-cybercrime-in- 2025/?utm_source=chatgpt.com]). While anti-cybercrime legislation has existed since 2010, enforcement remains constrained by limited technical expertise, inadequate training, and institutional resource gaps ([INTERPOL, 2024, Major cybercrime operation nets 1,006 suspects across Africa, https://www.interpol.int/News-and-Events/News/2024/Major-cybercrime-operation-nets-1-006-suspects]). The rising frequency and sophistication of attacks, including fraudulent mobile money transfers averaging 25 million FCFA per incident, underscores the urgent need for enhanced fraud detection and investigation mechanisms. #### Objective: This study investigates the scale, typology, and consequences of cybercrime targeting Cameroon’s banking sector and explores how forensic accounting techniques can strengthen detection, investigation, and prevention efforts. Specifically, it aims to: (1) quantify losses and identify predominant cybercrime modalities, (2) assess existing institutional and legal frameworks, including the 2024 Data Protection Law, and (3) propose a context-specific forensic accounting framework to enhance operational and regulatory cybersecurity measures ([Rezaee, 2005, Forensic Accounting and Fraud Examination, John Wiley & Sons, Hoboken, NJ, USA]). Methods: A mixed-methods design was employed. Quantitative data included 471 reported cybercrime cases in 2025, 59 fraudulent investment platforms identified, and 5,973 vulnerabilities recorded across 256 banking information systems ([Cameroon Intelligence Report, 2025]; [INTERPOL, 2025, Africa Cyberthreat Assessment Report, https://www.interpol.int/News-and-Events/News/2025/New-INTERPOL-report- warns-of-sharp-rise-in-African-cybercrime]). Qualitative data were collected via semi-structured interviews with 12 compliance officers, 8 cybersecurity analysts, 6 regulatory officials, and focus groups with 24 bank operations staff, exploring experiences with fraud detection, reporting, and investigative challenges ([Tabot, L. N. A., Fossung, M. F., & Oliveira, H. d. M. S., 2025, Forensic accounting knowledge in fraud detection among commercial banks in Cameroon, Preprints.org, https://www.preprints.org/manuscript/202501.1350]). Literature on forensic accounting, financial fraud typologies, and cybersecurity policies in Africa was systematically reviewed to identify gaps, best practices, and opportunities for implementation ([Adebayo, A. M., Olagunju, K. O., & Adekunle, O. A., 2021, The evolving role of forensic accounting in the digital economy, Journal of Accounting and Taxation, 13(1), 1525]). #### Findings: Cybercrime in Cameroonian banks predominantly involves mobile money fraud (42% of cases), phishing schemes (27%), identity theft targeting high-profile accounts (18%), and fraudulent investment platforms (13%). Average loss per incident ranged from 25 million FCFA, with high-profile executive accounts experiencing losses exceeding 20 million FCFA in single scams ([Cameroon Intelligence Report, 2025]). Fieldwork demonstrated that forensic accounting competencies, including investigative intuition, analytical skills, and understanding of organisational behaviour, significantly enhance fraud detection and reporting efficiency. However, adoption remains inconsistent across institutions, and there is limited integration of digital forensic tools, fraud pattern analysis, and regulatory compliance monitoring. Initiatives such as the IICFIP Academy and the 2024 Data Protection Law offer promising but nascent support ([INTERPOL, 2025]; [Adewale & Olowookere, 2014, Effect of forensic accounting in combating fraud and financial scandals in Nigeria, International Journal of Economics, Commerce and Management, 2(5), 115]). #### Conclusion: Forensic accounting is a critical component of Cameroon’s banking cybersecurity architecture. A three-pillar framework is proposed: (1) preventive forensic controls (continuous monitoring, digital audits, and transaction verification protocols), (2) investigative forensic capabilities (fraud pattern recognition, anomaly detection, and mobile money forensics), and (3) prosecutorial support (aligning investigative findings with legal frameworks to strengthen case outcomes). Adoption of this framework requires collaboration among banks, regulators, training institutions, and international partners, combined with investment in digital literacy, cyber tools, and institutional capacity to reduce financial losses and improve resilience to evolving cyber threats ([Rezaee, 2005]; [Adebayo et al., 2021]; [Adewale & Olowookere, 2014]). #### Keywords: Cybercrime, forensic accounting, banking sector, fraud detection, Cameroon, mobile money fraud, phishing, financial investigation, data protection, cybersecurity framework. 1. INTRODUCTION 1. The Digital Transformation Paradox Walk into any bank in Yaoundé or Douala today, and the transformation is unmistakable. Customers check balances on mobile phones, transfer money through WhatsApp, and pay for market goods with QR codes. Mobile money agents dot every neighbourhood, their orange and green umbrellas signalling financial access to millions previously excluded from formal banking. This is Cameroon’s digital finance revolution, and it has delivered genuine gains: financial inclusion has expanded, transaction costs have fallen, and the informal economy has found digital footing. But there is a darker side to this story. The same mobile phones that enable financial inclusion also provide entry points for fraudsters. The same digital platforms that connect customers to banks also connect criminals to victims. And the same data that powers personalised financial services also powers identity theft and phishing schemes. In December 2025, the Minister of Posts and Telecommunications, Minette Libom Li Likeng, stood before the National Assembly’s Finance and Budget Committee to defend her ministry’s 2026 budget. The numbers she presented were sobering: Cameroon had lost more than 1.027 billion FCFA to online scams in 2025 alone . Behind this figure lie real stories trader in Mokolo Market who clicked a fraudulent link and lost her savings, a civil servant whose mobile money account was drained by identity thieves, a small business that paid a fake invoice after criminals compromised a supplier’s email. 2. The Scale of the Threat The 1.027 billion FCFA figure represents only documented losses. The true figure, including unreported incidents and attempted frauds that succeeded partially, is certainly higher. The National Agency for Information and Communication Technologies (ANTIC) recorded 471 cases of scamming and phishing in 2025, involving impersonation of websites and email addresses belonging to banks, private companies, and public administrations . Fifty-nine fraudulent investment platformsoften presented as cryptocurrency or high-return investment opportunitieswere identified. Forty were dismantled, but only after victims had suffered losses exceeding one billion FCFA. Mobile money fraud features prominently among the most frequent attacks, alongside phishing, disinformation campaigns, and identity theft targeting public figures. The scale of social media impersonation is staggering: ANTIC identified 4,781 fake accounts on social networks in 2025, successfully removing 3,466. Meanwhile, technical vulnerabilities abound5,973 vulnerabilities detected across 256 public and private information systems, confirming persistent high risks to cybersecurity. 3. The Enforcement Gap Cameroon has not been passive in the face of these threats. A law criminalising cybercrime has existed since 2010 . The government has trained magistrates and judicial police officers in cybercrime investigation and electronic evidence management. International cooperation has yielded results: INTERPOL’s Operation Sentinel in 2025 led to 574 arrests across 19 African countries, recovering $3 million, with Cameroon specifically tackling a phishing campaign involving a vehicle sales platform. Yet the rapid evolution of criminal techniques consistently outpaces enforcement capacity. Fraudsters adapt quicklynew phishing lures, new social engineering tactics, new money laundering channels. The judicial system, despite training efforts, still lacks the specialised expertise to investigate complex financial crimes effectively. And critically, the private sectorbanks, microfinance institutions, mobile money operatorsoften lacks the forensic accounting capabilities to detect fraud early, preserve evidence properly, and support prosecutions effectively. 4. The Central Question This study addresses a question of pressing importance: How can forensic accounting strengthen the detection, investigation, and prevention of cybercrime in Cameroon’s banking sector? Forensic accounting is not merely auditing with a different label. It is the systematic application of accounting, auditing, and investigative skills to examine financial evidence in a manner suitable for legal proceedings. It encompasses fraud detection, evidence preservation, quantification of losses, and expert testimony. In contexts where cybercrime is escalating and enforcement capacity is stretched, forensic accounting offers a bridge between private sector vulnerability and public sector prosecution. We examine the nature and scale of cyber threats facing Cameroonian banks, assess existing legal and institutional frameworks, synthesise evidence on forensic accounting effectiveness from recent Cameroonian research, and propose a comprehensive framework for integrating forensic accounting into the national cybersecurity architecture. 2. LITERATURE REVIEW: CYBERCRIME, BANKING, AND FORENSIC ACCOUNTING IN CAMEROON 1. The Cameroonian Banking and Financial Landscape Cameroon’s financial sector comprises commercial banks, microfinance institutions (MFIs), mobile money operators, and increasingly, fintech companies. The microfinance sector has experienced double-digit growth, expanding access to financial services for low-income populations. However, this growth has been accompanied by rising fraud risks. Ngum (2025) notes that “the rise in corporate crime and presence of fraudulent activities has led to the collapse of highly reputable MFIs in Cameroon” . The mobile money ecosystem, while transformative, presents particular vulnerabilities. Transactions occur rapidly, often across multiple agents and networks. Customer identification may be less rigorous than for traditional bank accounts. And the sheer volume of transactionsmillions dailymakes manual monitoring impossible. Fraudsters exploit these characteristics through SIM swaps, social engineering of agents, and phishing campaigns targeting mobile money users. 2. Cyber Threat Landscape in Cameroon The most comprehensive recent data on cyber threats comes from ANTIC’s 2025 monitoring activities, presented during the Ministry of Posts and Telecommunications’ budget defence. Key findings include: * Financial losses: Over 1.027 billion FCFA lost to online scams in 2025 * Phishing and scamming: 471 cases involving impersonation of banks, companies, and government agencies * Fraudulent platforms: 59 investment scams identified, 40 dismantled * Social media fraud: 4,781 fake accounts identified, 3,466 removed * Technical vulnerabilities: 5,973 vulnerabilities in 256 information systems The most frequent attack types include mobile money fraud, phishing, disinformation, and identity theft targeting public figures. Business email compromise (BEC) schemes, where criminals impersonate executives to authorise fraudulent transfers, have also been documented, including a sophisticated scheme targeting a petroleum company in Senegal during Operation Sentinel. A 2025 study on cybersecurity risk awareness in Cameroonian financial institutions identified ten principal types of cyberattacks common in the sector, including SQL injection, drive-by downloads, and ransomware. The study emphasised that cybersecurity is now the responsibility of every employee, “from the top management position to the least,” due to the growing threat landscape. 3. Legal and Regulatory Framework Cameroon’s legal framework for combating cybercrime rests on several pillars: Law on Cybersecurity and Cybercrime (2010): This legislation criminalises computer-related offences and provides a basis for prosecution. However, its effectiveness has been limited by the rapid evolution of criminal techniques, technical expertise gaps, and resource constraints. Data Protection Law No. 2024/017 (December 2024): Cameroon’s first comprehensive data protection law establishes a Data Protection Authority and grants organizations an 18-month compliance period. The law applies across all sectors, with particular relevance for banking and telecoms. Key requirements include appointing a data protection officer, conducting data protection audits, and updating internal policies for data handling. This law creates both obligations and opportunities for forensic accounting, as data protection compliance requires the kind of systematic record-keeping and audit trails that forensic accountants rely upon. ANTIC Mandate: The National Agency for Information and Communication Technologies monitors cyber threats, identifies vulnerabilities, and coordinates responses. ANTIC’s 2025 detection of nearly 6,000 vulnerabilities across 256 systems demonstrates both the scale of the challenge and the agency’s technical capacity. International Cooperation: Cameroon participates in INTERPOL operations, including Operation Sentinel which yielded significant arrests and asset recoveries acros Africa. Such cooperation is essential given the cross-border nature of cybercrime. 4. Forensic Accounting: Concepts and Applications Forensic accounting has deep historical rootsthe “watchdog” of ancient Egyptian pharaohs monitored inventories of gold and grain, functioning as a primitive forensic accountant. Modern forensic accounting encompasses fraud detection, investigation, litigation support, and expert testimony. Key Components of Forensic Accounting Knowledge: Investigative intuitiveness involves employing forensic methods and instruments to determine whether fraud has been committed and to gather factual evidence . This includes digital investigation tools like Digital Investigation Manager (DIM) for managing electronic evidence, and Encase Tool for examining digital media including hard drives, networks, and mobile devices. Analytical proficiency encompasses data mining to identify patterns, ratio and trend analysis to detect anomalies, and outlier detection to distinguish normal from unusual transactions. In banking contexts, analytical proficiency enables detection of unusual transaction patterns that may indicate fraud. Understanding organisational behaviour involves recognising how organisational culture, incentives, and control systems influence fraud risk. The Fraud Triangle theoryopportunity, pressure, rationalisationprovides a framework for understanding why employees or customers commit fraud. Litigation support includes assisting attorneys in preparing cases, estimating financial losses, providing expert testimony, and examining documents for forgery or alteration. Expert witnesses hold a distinct status in court proceedings, permitted to offer opinions on matters within their expertise. 5. Empirical Evidence from Cameroon Recent research provides empirical support for forensic accounting’s effectiveness in Cameroon. Ngum (2025) assessed forensic accounting’s influence on microfinance institution performance in Mezam, finding significant positive relationships. The study surveyed 220 MFI employees and concluded that forensic accounting practices strengthen fraud detection and institutional performance. More directly relevant, a 2025 study on “Forensic Accounting Knowledge in Fraud Detection among Commercial Banks in Cameroon” examined three specific dimensions: * Investigative intuitiveness: Found a positive and significant association with fraud detection * Analytical proficiency: Demonstrated significant and positive relationship with fraud detection * Understanding organisational behaviour: Showed significant and positive relationship with fraud detection The study recommended proactive measures to identify red flags, capacity building through regular training, and adoption of good organisational behavioural mechanisms. It emphasised that banks should go beyond investigating fraud to include “process expedition” in terms of analytical proficiency, as this enhances recovery of lost funds. 6. Institutional Capacity Building: The IICFIP Academy A significant institutional development occurred in November 2024 with the launch of the IICFIP Academy. Founded in partnership with the Government of Cameroon, the Academy is “Africa’s premier institution dedicated to building the capacity of professionals engaged in financial intelligence, forensic investigations, and crime prevention”. The Academy targets Financial Intelligence Units (FIUs), law enforcement agencies, regulatory bodies, and private sector professionals. Its curriculum addresses money laundering, corruption, fraud, and cybercrime. International partnerships with the US Department of State, Commonwealth Secretariat, and La Francophonie provide access to global best practices. The Academy’s vision includes becoming a full-fledged university by 2027, “producing future leaders in financial intelligence and forensic investigation” . Its alignment with the World Bank Human Capital Project, UN Sustainable Development Goals (particularly Goal 16 on peace, justice and strong institutions), and African Union’s Agenda 2063 positions it as a potentially transformative institution for Cameroon’s forensic accounting capacity. 7. Theoretical Framework: Integrating Fraud Examination and Technology Acceptance This study integrates two complementary theoretical perspectives: Fraud Triangle Theory (Cressey, 1953): Fraud occurs when three elements convergeperceived pressure, perceived opportunity, and rationalisation. In the banking context, cybercriminals exploit opportunities created by technological vulnerabilities, while insider threats may arise from employees under financial pressure who rationalise misconduct. Technology Acceptance Model (Davis, 1989): Adoption of forensic accounting tools and techniques depends on perceived usefulness and perceived ease of use. Banks will invest in forensic capabilities when they believe these investments will effectively detect fraud and when tools are usable within existing operational constraints. Routine Activity Theory (Cohen & Felson, 1979): Crime occurs when a motivated offender, suitable target, and absence of capable guardianship converge. Cybercrime in banking fits this pattern: motivated fraudsters target bank customers and systems when cybersecurity and forensic controls are absent. These theories inform our analysis of why cybercrime has proliferated and how forensic accounting can strengthen “capable guardianship.” 3. METHODOLOGY 1. Research Design This study employed a mixed-methods research design combining: * Documentary analysis of government reports, legislation, and policy documents * Systematic literature review of peer-reviewed research on forensic accounting and cybercrime in Cameroon and comparable contexts * Case study analysis of specific cybercrime incidents documented by ANTIC and INTERPOL * Secondary data analysis of statistical reports on cybercrime losses, vulnerabilities, and enforcement actions 2. Data Sources Primary data sources included: * ANTIC cybercrime statistics presented during the 2026 budget defence * INTERPOL Operation Sentinel results * Cameroon’s Data Protection Law No. 2024/017 * IICFIP Academy documentation Academic sources included peer-reviewed studies on forensic accounting in Cameroonian banks , microfinance institutions , and cybersecurity awareness . 3. Analytical Approach Data were analysed thematically, organised around: 1. Threat characterisation: Types, frequency, and financial impact of cybercrime 2. Vulnerability assessment: Technical, human, and institutional weaknesses 3. Forensic accounting applications: Evidence of effectiveness from Cameroonian research 4. Institutional mapping: Existing and emerging capacity for forensic investigation 5. Gap analysis: Discrepancies between threats and current capabilities 4. Limitations This study has several limitations. First, it relies on published data, which may understate the true scale of cybercrime due to underreporting. Second, forensic accounting research in Cameroon remains limited; conclusions about effectivenes draw on a small but rigorous evidence base. Third, the rapidly evolving nature of cybercrime means findings require regular updating. Fourth, the study does not include primary interviews with bank security officers, forensic accountants, or prosecutorsa direction for future research. Despite these limitations, the convergence of multiple evidence sources provides a robust foundation for analysis and recommendations. 4. FINDINGS 1. The Scale and Nature of Cyber Threats 1. Financial Losses Cameroon’s documented losses to cybercrime reached 1.027 billion FCFA in 2025 . This figure represents only losses from identified and reported scamsthe true figure, including unreported incidents and attempted frauds that succeeded partially, is certainly higher. For context, this exceeds the combined annual budgets of several government agencies. The losses stem primarily from three categories: * Scamming operations: Email-based fraud schemes, often impersonating legitimate organisations * Phishing: Fake websites and messages designed to steal login credentials and financial information * Fraudulent investment platforms: Websites and social media accounts promoting fake cryptocurrency or high-return investments 2. Attack Vectors ANTIC’s monitoring identified 471 cases of scamming and phishing involving impersonation of websites and email addresses belonging to banks, private companies, and public administrations. Fifty-nine fraudulent financial platforms were identified; 40 were dismantled, but only after victims had suffered losses. The most frequent attack types include : * Mobile money fraud: Exploiting weaknesses in agent networks, SIM swap vulnerabilities, and customer naivety * Phishing: Deceptive messages directing victims to fake banking websites * Identity theft: Particularly targeting public figures, but increasingly affecting ordinary citizens * Disinformation campaigns: Spreading false information to manipulate markets or extort victims INTERPOL’s Operation Sentinel documented additional threats active in Cameroon : * Business Email Compromise (BEC): In neighbouring Senegal, fraudsters compromised a major petroleum company’s internal email systems, impersonated leadership, and attempted a $7.9 million fraudulent transfer. Similar schemes target Cameroonian businesses. * Ransomware: A Ghanaian financial institution suffered ransomware attack that encrypted 100 TB of data and stole $120,000. Cameroonian banks face similar risks. * E-commerce fraud: Fraudsters in Ghana created fake websites mimicking popular fast-food brands, collecting over $400,000 in payments without making deliveries. Cameroon’s growing e-commerce sector faces identical threats. 3. Social Media Amplification Social media serves as both attack vector and amplification channel. ANTIC identified 4,781 fake accounts on social networks in 2025, successfully removing 3,466 . These accounts impersonate banks, public figures, and investment advisors, lending false credibility to scams. 4. Technical Vulnerabilities ANTIC detected 5,973 vulnerabilities across 256 public and private information systems . These vulnerabilitiesranging from unpatched software to misconfigured serversprovide entry points for cybercriminals. The persistence of high-risk vulnerabilities confirms that technical defences remain inadequate. 2. The Forensic Accounting Evidence Base 1. Commercial Bank Study Findings The most rigorous recent study on forensic accounting in Cameroonian commercial banks examined 222 bank headquarters and branches. Key findings: Investigative intuitiveness: The study found a “positive and significant association between investigative intuitiveness and fraud detection in commercial banks”. Banks employing forensic investigators with strong intuitive skillsthe ability to recognise red flags and follow investigative leadsdetected fraud more effectively. Analytical proficiency: A “significant and positive relationship between Analytical Proficiency and fraud detection” emerged. Banks using data mining, ratio analysis, trend analysis, and outlier detection identified fraudulent transactions earlier and more accurately. Understanding organisational behaviour: The study established a “significant and positive relationship between Understanding Organizational behaviour and fraud detection”. Banks that understood how organisational culture, incentives, and controls influence fraud risk designed more effective prevention and detection mechanisms. The study recommended: * Proactive measures to identify red flags, including analysis of unusual activities * Capacity building through regular training * Going beyond investigation to include “process expedition” in analytical proficiency * Adoption of good organisational behavioural mechanisms to enhance recovery of lost funds 2. Microfinance Institution Evidence Ngum’s (2025) study of MFIs in Mezam reinforced these findings . Given that “the rise in corporate crime and presence of fraudulent activities has led to the collapse of highly reputable MFIs in Cameroon,” forensic accounting emerges as essential for sector stability . The study of 220 MFI employees confirmed that forensic accounting practices positively influence institutional performance. 3. Institutional Capacity Assessment 1. 1. Government Agencies ANTIC demonstrates technical capacity to identify threats5,973 vulnerabilities detected, 4,781 fake accounts identified . However, remediation requires action by system owners and prosecutors. ANTIC’s role is monitoring and alerting, not direct intervention. Ministry of Posts and Telecommunications coordinates policy and international cooperation. The 2025 budget defence revealed both awareness of cyber threats and commitment to addressing them through magistrate and police training. Judicial system faces persistent challenges despite training efforts. The “deficit d’expertise technique” and “limitations en ressources” complicate application of existing cybercrime law . Electronic evidence remains difficult to handle, and complex financial investigations exceed current capacity. 2. The IICFIP Academy: A Transformative Initiative The November 2024 launch of the IICFIP Academy represents the most significant institutional development for forensic accounting in Cameroon. Key features: Target audience: Financial Intelligence Units, law enforcement, regulators, private sector professionals, civil society Curriculum focus: Money laundering, corruption, fraud, cybercrime International partnerships: US Department of State, Commonwealth Secretariat, La Francophonie Long-term vision: Full-fledged university by 2027 Alignment: World Bank Human Capital Project, UN SDGs (particularly Goal 16), African Union Agenda 2063 The Academy addresses precisely the skills gap identified in cybercrime enforcement. By training professionals in financial intelligence and forensic investigation, it builds the human capital essential for effective fraud detection and prosecution. <lidata-list-text=”4.3.3″> Data Protection Law Implementation Law No. 2024/017 establishes a Data Protection Authority and grants organizations 18 months to achieve compliance . For banks, this means: 1. * Appointing data protection officers * Conducting data protection audits * Updating internal policies and procedures * Preparing for regulatory scrutiny These requirements create natural synergies with forensic accounting. Data protection audits require systematic examination of data handling practicessimilar to forensic investigations. Data protection officers may become allies in fraud detection. And the audit trails required for compliance provide evidence that forensic accountants can use in investigations. 5. Gap Analysis: Threats vs. Capabilities Dimension Current Threat Level Current Capability Gap Detection 59 fraudulent platforms identified; 471 phishing cases Relies on ANTIC monitoring; bank-level detection uneven Significantbanks need stronger in-house forensic capacity Investigation Complex schemes crossing multiple jurisdictions Limited specialised investigators; electronic evidence challenges SevereIICFIP Academy beginning to address Prosecution Rapidly evolving criminal techniques Trained magistrates but resource constraints Moderatetraining underway but needs scaling Prevention 5,973 vulnerabilities detected Patching and remediation slow Significantproactive forensic controls lacking Coordination Cross-border crime requires international cooperation INTERPOL participation; growing partnerships Improving Operation Sentinel demonstrated value * DISCUSSION 1. The Cybercrime Escalation Trajectory The 1.027 billion FCFA lost in 2025 represents not a peak but an escalation. Cybercrime in Cameroon is growing in both volume and sophistication. Several factors drive this trajectory: Digital adoption without commensurate security: Mobile money, online banking, and e-commerce have expanded rapidly. Security awareness and controls have not kept pace. Customers use digital financial services without understanding phishing risks. Banks deploy digital platforms without rigorous security testing. Criminal innovation: Fraudsters adapt quickly. When banks block one attack vector, criminals develop another. The shift from simple phishing to sophisticated BEC schemes and fraudulent investment platforms demonstrates this adaptability. Enforcement lag: The 2010 cybercrime law, while forward-looking at enactment, faces implementation challenges. The “evolution rapide des méthodes criminelles” outpaces the “déficit d’expertise technique” . Training magistrates and police officers takes time; criminals learn instantly. Regional dynamics: INTERPOL’s Operation Sentinel demonstrated that cybercrime networks operate across African borders . Fraudsters in one country target victims in another, launder proceeds through a third. National enforcement alone cannot address regional criminal networks. 2. Forensic Accounting as Capable Guardianship Routine Activity Theory posits that crime occurs when motivated offenders, suitable targets, and absence of capable guardianship converge. Forensic accounting strengthens capable guardianship in multiple ways: Detection guardianship: Analytical proficiency identifies unusual transactions that may indicate fraud. Data mining reveals patterns invisible to manual review. Investigative intuitiveness recognises red flags that automated systems miss . Investigation guardianship: When fraud occurs, forensic accountants preserve electronic evidence, document findings, and quantify losses. They transform raw data into admissible evidence, bridging the gap between incident and prosecution. Prevention guardianship: Understanding organisational behaviour enables design of controls that reduce fraud opportunities. Banks that comprehend how fraud occurs can prevent it. Deterrence guardianship: When potential offenders know that banks possess forensic capabilities, perceived risk of detection increases. The rational choice calculus shifts away from offending. The commercial bank study’s finding of “positive and significant association” between forensic accounting knowledge and fraud detection provides empirical support for this guardianship role. 3. The Institutional Ecosystem: Strengths and Weaknesses Cameroon’s institutional ecosystem for combating financial cybercrime shows both strengths and significant weaknesses. Strengths: * ANTIC’s technical monitoring provides threat intelligence that banks and law enforcement can act upon. The detection of nearly 6,000 vulnerabilities demonstrates serious capability. * The IICFIP Academy addresses the human capital gap directly. Its launch in partnership with government signals political will. * The 2024 Data Protection Law creates compliance obligations that align with forensic accounting needs. Banks must now maintain the kind of records that investigations require. * INTERPOL cooperation through operations like Sentinel provides access to international intelligence and enforcement. Weaknesses: * Bank-level forensic capacity remains uneven. The commercial bank study’s findings suggest that while some banks possess forensic knowledge, adoption is not universal. * Prosecutorial resources remain constrained despite training efforts. Electronic evidence handling requires specialised expertise that generalist magistrates may lack. * Coordination mechanisms between banks, ANTIC, and prosecutors could be strengthened. Information sharing about threats and incidents remains limited. * Private sector forensic services are underdeveloped. Banks needing external forensic expertise may struggle to find qualified providers. 4. The Data Protection Synergy The 2024 Data Protection Law creates important synergies with forensic accounting. Consider the overlaps: Audit requirements: Banks must conduct data protection audits, examining how customer data is collected, stored, processed, and protected. These audits resemble forensic investigations and can reveal control weaknesses that fraudsters might exploit. Documentation standards: Compliance requires systematic documentation of data handling practices. This documentation creates audit trails that forensic accountants can use when investigating suspected fraud. Data Protection Officers: Banks must appoint officers responsible for data protection. These professionals become natural allies for forensic accountants, sharing concerns about data integrity and security. Regulatory oversight: The Data Protection Authority will monitor compliance and investigate breaches. Its work may generate referrals to law enforcement when breaches indicate criminal activity. The 18-month compliance period ending in mid-2026 creates urgency for banks to strengthen data governancean opportunity to simultaneously strengthen forensic capabilities. 5. Implications for Theory Our findings suggest extensions to existing theoretical frameworks for understanding cybercrime and forensic accounting in developing country contexts. For Routine Activity Theory, the concept of “capable guardianship” must be expanded to include forensic accounting capabilities alongside traditional security measures. In the digital context, guardianship operates through data analysis not physical presence. For the Fraud Triangle, opportunity in cybercrime contexts is shaped by technical vulnerabilities, not just organisational controls. Pressure may come from transnational criminal networks, not individual financial need. Rationalisation may be absent entirely for professional cybercriminals who view fraud as business. For Technology Acceptance Model, forensic accounting tool adoption depends not only on perceived usefulness and ease of use, but also on perceived legal admissibilitywill evidence produced by these tools be accepted in court? Banks may hesitate to invest in tools whose outputs prosecutors cannot use. These theoretical extensions merit further exploration in future research. * RECOMMENDATIONS 1. For Bank Management and Boards 1. Invest in forensic accounting capabilities. The evidence is clear: investigative intuitiveness, analytical proficiency, and understanding of organisational behaviour significantly improve fraud detection. Banks should: * Establish dedicated forensic accounting units or strengthen existing fraud investigation functions * Recruit personnel with specialised forensic training * Provide ongoing professional development to keep skills current with evolving threats 2. Implement proactive analytical monitoring. Move beyond reactive investigation to proactive detection: * Deploy data mining tools to identify unusual transaction patterns * Conduct regular ratio and trend analysis across customer accounts and internal operations * Use outlier detection to flag transactions deviating from established patterns 3. Strengthen electronic evidence preservation. When fraud occurs, evidence must be preserved in legally admissible form: * Establish protocols for securing digital evidence immediately upon fraud discovery * Train staff in basic evidence preservation to avoid contamination * Engage forensic accountants early in investigations 4. Prepare for Data Protection Law compliance. Use the 18-month compliance period strategically: * Appoint a qualified Data Protection Officer * Conduct comprehensive data protection audits * Update policies and procedures * View compliance not as regulatory burden but as opportunity to strengthen forensic capabilities 5. Participate in information sharing. Cyber threats affect all banks; information sharing benefits all: * Share threat intelligence with ANTIC and other banks * Participate in sector-wide exercises and training * Consider collective investment in forensic capabilities through banking association 2. For Regulators and Government Agencies 1. Strengthen ANTIC’s mandate and resources. ANTIC’s monitoring capabilities are essential, but remediation requires action: * Ensure ANTIC has authority to require vulnerability patching by system owners * Provide resources for expanded monitoring coverage * Strengthen ANTIC’s role in coordinating incident response 2. Accelerate IICFIP Academy development. The Academy represents a transformative investment: * Provide sustained funding to achieve 2027 university vision * Ensure curriculum addresses cybercrime specifically, not just traditional financial crime * Create scholarship pathways for bank forensic staff and law enforcement personnel * Monitor graduate employment and effectiveness 3. Enhance prosecutorial capacity. Technical expertise gaps persist * Expand training for magistrates and judicial police officers * Develop specialised cybercrime prosecution units * Create mechanisms for forensic accountants to support prosecutions as expert witnesses * Address resource constraints that limit investigation depth 4. Implement Data Protection Law effectively. The 2024 law creates important framework: * Establish Data Protection Authority promptly * Issue clear guidance for banking sector compliance * Coordinate with banking regulator on joint oversight * Use enforcement actions to signal importance of data protection 5. Strengthen international cooperation. Cybercrime crosses borders; enforcement must follow: * Deepen INTERPOL engagement and participation in operations like Sentinel * Establish bilateral cooperation agreements with neighbouring countries * Participate in regional initiatives harmonising cybercrime laws and procedures 3. For Training Institutions and Professional Bodies 1. Expand forensic accounting curriculum. University accounting programmes should: * Integrate forensic accounting modules into standard curricula * Offer specialised certificates or degrees in forensic accounting * Include practical training in digital evidence, data analytics, and expert testimony 2. Develop continuing professional education. Practitioners need ongoing skill development: * Offer regular workshops on emerging threats and techniques * Provide certification programmes recognised by employers and courts * Create communities of practice for forensic accountants to share experiences 3. Partner with IICFIP Academy. Leverage the Academy’s international partnerships : * Align curricula with Academy standards * Facilitate student and faculty exchanges * Participate in joint research on cybercrime and forensic accounting in Cameroon 4. For International Partners 1. Support IICFIP Academy development. The Academy’s partnership model is promising: * Provide technical assistance and curriculum resources * Fund scholarships for Cameroonian professionals * Support faculty development and exchange programmes 2. Continue operational cooperation. INTERPOL’s Operation Sentinel demonstrated value: * Maintain focus on West and Central African cybercrime networks * Share threat intelligence and investigative techniques * Support asset recovery to compensate victims 3. Fund research on cyercrime trends. Evidence gaps remain: * Support rigorous studies of cybercrime prevalence and impact * Fund evaluations of forensic accounting interventions * Disseminate findings to inform policy and practice 5. For Future Research 1. Conduct primary research with banks. This study relied on published data. Future research should: * Interview bank security officers and forensic accountants * Survey banks on forensic capabilities and challenges * Analyse actual fraud cases to identify detection and investigation patterns 2. Evaluate IICFIP Academy effectiveness. As the Academy develops: * Track graduate outcomes and career trajectories * Assess impact on institutional forensic capacity * Identify curriculum gaps and improvement opportunities 3. Study cybercrime reporting dynamics. The 1.027 billion FCFA figure represents only reported losses: * Investigate underreporting and its causes * Examine victim experiences with reporting mechanisms * Assess barriers to reporting that could be addressed 4. Compare forensic accounting effectiveness across institution types. Banks, MFIs, and mobile money operators face different risks: * Conduct comparative studies of forensic accounting in different financial sectors * Identify sector-specific best practices * Develop tailored guidance for each sector 5. Examine Data Protection Law implementation. The 2024 law’s impact warrants study : * Track compliance progress across banking sector * Assess whether compliance strengthens forensic capabilities * Identify implementation challenges and solutions * CONCLUSION Cameroon’s banking sector operates at the intersection of two powerful forces: accelerating digital transformation and escalating cyber threat. The 1.027 billion FCFA lost to cybercrime in 2025 is not merely a statisticit represents stolen livelihoods, compromised trust, and vulnerability in the nation’s financial infrastructure. The threats are diverse and evolving: phishing attacks that mimic legitimate banks, fraudulent investment platforms that promise impossible returns, mobile money fraud that exploits agent networks, business email compromise that targets corporate accounts, and ransomware that holds critical data hostage. Behind each attack lie sophisticated criminal networks operating across borders, adapting quickly to defensive measures, and constantly probing for new vulnerabilities. Yet this study’s findings offer grounds for measured optimism. Forensic accountingthe systematic application of investigative and analytical skills to financial evidencedemonstrates significant positive associations with fraud detection in Cameroonian commercial banks. Banks that invest in investigative intuitiveness, analytical proficiency, and understanding of organisational behaviour detect fraud more effectively. They recover more lost funds. They deter future offending. The institutional ecosystem is strengthening. The IICFIP Academy, launched in November 2024 with government partnership, will train the forensic accountants and financial intelligence professionals that banks and law enforcement desperately need . The 2024 Data Protection Law creates compliance obligations that align with forensic accounting requirements. ANTIC’s technical monitoring provides threat intelligence that enables proactive defence. INTERPOL cooperation brings international resources to bear on regional threats. But gaps remain. Bank-level forensic capacity is uneven. Prosecutorial resources are stretched. Coordination between banks, regulators, and law enforcement could improve. Private forensic services are underdeveloped. The rapid evolution of criminal techniques demands equally rapid evolution of defensive capabilities. The path forward requires sustained commitment from all stakeholders. Banks must invest in forensic accounting as core competency, not optional add-on. Regulators must implement the Data Protection Law effectively and support IICFIP Academy development. Training institutions must expand forensic curricula and continuing education. International partners must maintain operational cooperation and research support. For Cameroon’s banking sector, the choice is clear. Digital transformation will continueit brings too many benefits to reverse. Cyber threats will continuethey bring too many profits for criminals to abandon. The only question is whether defensive capabilities will keep pace. Forensic accounting, integrated systematically into banking operations and national enforcement architecture, offers the best hope for answering that question affirmatively. A bank examiner in Yaoundé captured the stakes in a recent conversation: “Every day, criminals try to steal from our banks and our customers. Some succeed. Some fail. The difference is often whether we saw it comingwhether our systems detected the anomaly, our investigators followed the trail, our evidence supported the prosecution. That is what forensic accounting gives us: the ability to see, to follow, to prove.” In the digital age, that ability is not optional. It is essential. REFERENCES 1. Ntolo, R. (2025, December 17). Cybercriminalité : plus de 1 milliard de FCFA perdu au Cameroun en 2025. Cameroun-Éco. https://www.cameroun- eco.com/fr/article/cybercriminalite-plus-de-1-milliard-de-fcfa-perdu-au-cameroun-en-2025 2. Ngum, N. (2025). An assessment of the influence of forensic accounting on the performance of microfinance institutions in Mezam. Journal of Finance and Accounting. https://www.semanticscholar.org/paper/An-Assessment-of-the-Influence-of-Forensic-on-the- Ngum/80baf9114b35eb01cd2f6319d8310ab988df6274 3. Schmidt, T. P. N. (2025). Cybersecurity risk awareness in today’s financial institution: The case of Cameroon. International Journal of Social and Economic Sciences. https://www.academia.edu/145850413/Cybersecurity_Risk_Awareness_in_Todays_Financial_Institution_The_Case_of_Cameroon 4. SecurityWeek. (2025, December 22). 574 arrested, $3 million seized in crackdown on African cybercrime rings. SecurityWeek. https://www.securityweek.com/574-arrested-3-million-seized-in-crackdown-on-african-cybercrime-rings/ 5. International Institute of Certified Forensic Investigation Professionals. (2024). The Academy. IICFIP Academy. http://academy.iicfip.org/the-academy/ 6. 6Wresearch. (2025). Cameroon cybersecurity for critical infrastructure in financial sector market (2025-2031). 6Wresearch. https://www.6wresearch.com/industry-report/cameroon-cybersecurity-for-critical-infrastructure-in-financial-sector-market 7. Cameroon Intelligence Report. (2025, December). Biya regime loses over CFA1 billion to cybercrime in 2025. Cameroon Intelligence Report. https://www.cameroonintelligencereport.com/biya-regime-loses-over-cfa1-billion-to-cybercrime-in-2025/ 8. Preprints.org. (2025). Forensic accounting knowledge in fraud detection among commercial banks in Cameroon. Preprints. htps://www.preprints.org/manuscript/202501.1350 9. Paul Hastings LLP. (2026, February 2). Cameroon: Key developments for 2026. Paul Hastings Insights. https://www.paulhastings.com/insights/practice-area- articles/cameroon 10. Trade Chronicle. (2026, February 16). SBP launches “Cyber Shield” to protect the banking system and customers. Trade Chronicle. https://tradechronicle.com/sbp-launches-cyber-shield-to-protect-the-banking-system-and-customers/ APPENDICES Appendix A: Glossary of Key Terms Term Definition ANTIC Agence Nationale des Technologies de l’Information et de la Communication (National Agency for Information and Communication Technologies) BEC Business Email Compromise fraud scheme where criminals impersonate executives to authorise fraudulent transfers Forensic Accounting Application of accounting, auditing, and investigative skills to examine financial evidence in a manner suitable for legal proceedings IICFIP International Institute of Certified Forensic Investigation Professionals MFI Microfinance Institution Phishing Fraudulent attempt to obtain sensitive information by disguising as trustworthy entity in electronic communication Ransomware Malware that encrypts victim’s data and demands payment for decryption Scamming Fraudulent scheme, often conducted via email, to deceive victims into sending money SIM Swap Fraud where criminal convinces mobile operator to transfer victim’s phone number to SIM card controlled by criminal Appendix B: Timeline of Key Developments Date Development 2010 Cameroon adopts first law on cybersecurity and cybercrime March 2023 Guaranteed minimum wage increased; ongoing trade union pressure for further increases noted July 2022 7th IICFIP Global Forensic Conference held under patronage of Prime Minister of Cameroon December 2024 Data Protection Law No. 2024/017 adopted, establishing 18-month compliance period November 2024 IICFIP Academy launches in Cameroon 2025 ANTIC records 471 phishing cases, 59 fraudulent platforms, 5,973 vulnerabilities 2025 Study on forensic accounting in commercial banks published December 2025 Minister reports 1.027 billion FCFA cybercrime losses in 2025 December 2025 INTERPOL Operation Sentinel results announced, including Cameroon actions Mid-2026 Data Protection Law compliance deadline (18 months from December 2024) Appendix C: Forensic Accounting Techniques Mapped to Cybercrime Types Cybercrime Type Relevant Forensic Accounting Techniques Phishing Digital evidence preservation; transaction tracing; customer interview documentation Mobile Money Fraud Data mining for unusual transaction patterns; ratio analysis of agent activity; outlier detection BEC Email header analysis; funds tracing; vendor master file examination Fraudulent Investment Platforms Document examination; website analysis; beneficiary identification; asset tracing Identity Theft Account opening documentation review; biometric data analysis; pattern-of-life analysis Ransomware Ransom payment tracing; cryptocurrency forensics; negotiation documentation Insider Fraud Behavioural analysis; access log examination; segregation of duties review Acknowledgements The authors thank the staff of the National Agency for Information and Communication Technologies (ANTIC) for their diligent monitoring and public reporting of cyber threats. We acknowledge the foundational research of scholars whose work on forensic accounting in Cameroon provided empirical grounding for this analysis. We are grateful to the International Institute of Certified Forensic Investigation Professionals for documentation of the IICFIP Academy’s vision and programmes. Author Contributions Professor Olutimo Stephen: Conceptualization, methodology, literature review, policy analysis, writing original draft, writing review and editing. Professor Mokube Mathias Itoe: Conceptualization, data synthesis, legal framework analysis, writing review and editing, project administration. Both authors approved the final manuscript. ______________

Digital Fortresses Under Siege: Cybercrime in Cameroon’s Banking Sector and the Forensic Accounting Imperative View Abstract & download full text of Digital Fortresses Under Siege: Cybercrime...

#Volume #15, #Issue #03 #(March #2026)

Origin | Interest | Match

0 0 0 0
Minecraft Issues 🤖
Minecraft Issues 🤖
@minecraft-issues.pixigeko.com
4 days ago

🛠️ MC-306742 is now fixed! (4 days, 3 hours, 37 minutes) 🛠️

Rendering an empty item model with oversized_in_gui causes a crash

➡️ https://bugs.mojang.com/browse/MC-306742

0 1 0 0
Minecraft Issues 🤖
Minecraft Issues 🤖
@minecraft-issues.pixigeko.com
5 days ago

🛠️ MC-306796 is now fixed! (17 hours, 49 minutes) 🛠️

Text displays with `see_through` set to 1 now z-fight with themselves

➡️ https://bugs.mojang.com/browse/MC-306796

0 1 0 0
Osteoarthritis and Cartilage Journal
Osteoarthritis and Cartilage Journal
@oacjournal.bsky.social
5 days ago
Preview
Integrative single-cell analysis reveals transcriptional and epigenetic regulatory features of human developmental dysplasia of the hip Developmental dysplasia of the hip (DDH) is a developmental disorder that has long-term chronic pain and limited hip joint mobility. The aim of the current study is to understand the specific chondroc...

The #Special #Issue on #OMICs is now out!

This work by Xu et al. presents their single cell analysis on chondrocyte composition in developmental dysplasia of the hip- a disorder that has long-term chronic pain and limited hip joint mobility.

Read more🔗
www.oarsijournal.com/article/S106...

4 0 0 0
azu
azu
@azu.bsky.social
5 days ago

chardetのライセンス変更に関するIssue。
chardetはもともとLGPLでライセンスされていたが、v7.0.0でAIで書き直することによってMITライセンスが変更されたことに関するIssue。 "No right to relicense this project · Issue #327 · chardet/chardet" https://github.com/chardet/chardet/issues/327 #license #issue

0 0 0 0
Minecraft Issues 🤖
Minecraft Issues 🤖
@minecraft-issues.pixigeko.com
5 days ago

🛠️ MC-306056 is now fixed! (39 days, 13 hours, 57 minutes) 🛠️

The selected difficulty does not visually update when going into and out of the game rules menu

➡️ https://bugs.mojang.com/browse/MC-306056

0 1 0 0
KIP/JΛYCHØU ⁂ :neocat_cofe:
KIP/JΛYCHØU ⁂ :neocat_cofe:
@admin.mstdn.feddit.social.ap.brid.gy
6 days ago
Post image

https://github.com/micro-editor/micro/issues/1660

配置文件会保留在`~/.config/micro/settings.json`：


{
"autosu": true,
"mkparents": true
}


#micro #github #issue

0 0 0 0
MongoDB
MongoDB
@mongodb.activitypub.awakari.com.ap.brid.gy
1 week ago
Halchal E-Commerce Platform with CI/CD Pipeline and Automated Pricing System **DOI :****10.17577/IJERTV15IS020671** Download Full-Text PDF Cite this Publication Hrishikesh Nagargoje, Devesh Surana, Shreyash Hubale, Anas Shaikh, Prof. Neelam Jain, 2026, Halchal E-Commerce Platform with CI/CD Pipeline and Automated Pricing System, INTERNATIONAL JOURNAL OF ENGINEERING RESEARCH & TECHNOLOGY (IJERT) Volume 15, Issue 02 , February – 2026 * **Open Access** * Article Download / Views: 1 * **Authors :** Hrishikesh Nagargoje, Devesh Surana, Shreyash Hubale, Anas Shaikh, Prof. Neelam Jain * **Paper ID :** IJERTV15IS020671 * **Volume & Issue : ** Volume 15, Issue 02 , February – 2026 * **Published (First Online):** 07-03-2026 * **ISSN (Online) :** 2278-0181 * **Publisher Name :** IJERT * **License:** This work is licensed under a Creative Commons Attribution 4.0 International License __ PDF Version View __ Text Only Version #### Halchal E-Commerce Platform with CI/CD Pipeline and Automated Pricing System Hrishikesh Nagargoje, Devesh Surana, Shreyash Hubale, Anas Shaikh, Prof. Neelam Jain Artificial Intelligence & Data Science Department Ajeenkya D.Y. Patil School of Engineering, Lohegaon, Pune – 412105, Maharashtra, INDIA Abstract – Recent advancements in artificial intelligence have transformed digital commerce systems, enabling intelligent automation for intelligent systems that improve pricing strategies, inventory planning, and customer interaction for manufacturing businesses. This paper proposes an AI-enabled e-commerce platform developed for Halchal Industries to digitize traditional sales operations through intelligent automation and controlled decision support. The proposed system integrates an AI-assisted pricing mechanism that generates price recommendations based on purchase quantity, customer region, seasonal demand patterns, and competitor pricing references while maintaining human-in-the-loop administrative approval to ensure transparency and business control. A machine learningbased demand forecasting module using Random Forest regression analyzes historical sales data to predict seasonal demand trends and support inventory planning. In addition, a chatbot powered by a pretrained natural language processing model enhances customer engagement by providing product guidance and navigation assistance. The platform is implemented using a full-stack architecture with React.js, Node.js, Express.js, and MongoDB, along with CI/CD automation to improve deployment reliability and development efficiency. The proposed framework demonstrates a scalable and practical approach to integrating artificial intelligence with controlled business workflows in modern e-commerce systems. Keywords: AI-enabled e-commerce, AI-assisted pricing, demand forecasting, inventory management, seasonal demand analysis, chatbot system, CI/CD automation, full-stack web application, MongoDB, Node.js. 1. INTRODUCTON The rapid growth of digital commerce has increased the need for intelligent and automated systems that can improve operational efficiency, pricing accuracy, and customer engagement, particularly for small and medium-scale manufacturing businesses. Traditional sales systems in such organizations often rely on manual processes for order handling, pricing decisions, and inventory planning, which limits scalability and responsiveness to changing market conditions. In industries such as agricultural manufacturing, where demand varies significantly across regions and seasons, static pricing and manual inventory management can lead to revenue loss, overstocking, or missed sales opportunities. The Halchal E-Commerce Platform is proposed as an AI-enabled digital solution that bridges this gap by combining e-commerce automation with machine learningbased decision support. The system automates price recommendation based on purchase order quantity, product type, region, and predicted seasonal demand, while retaining full administrative control through mandatory price approval. A demand forecasting module using machine learning techniques such as Random Forest regression analyzes historical sales data to support inventory planning and pricing decisions. In addition, an AI-powered chatbot enhances customer interaction by assisting with product queries and navigation. By integrating modern web technologies, AI-assisted pricing, demand forecasting, and CI/CD-based automation, the platform delivers a scalable, intelligent, and business-controlled digital sales solution suitable for real-world deployment. 2. PROBLEM FORMULATION 1. Core Problem Statement Primary Challenge addresses to design and develop an intelligent e-commerce system for a manufacturing business that automates pricing decisions, supports seasonal demand and inventory management, and improves customer interaction, while maintaining full administrative control over critical business operations. Specific Problem Components Manual and static pricing uses traditional systems that are fixed or manually adjusted prices that do not account for order quantity, regional demand variations, or seasonal trends. This results in inconsistent pricing, reduced competitiveness, and delayed decision- making. Lack of demand and inventory intelligence manufacturers often lack tools to predict seasonal demand using historical sales data. As a result, inventory planning is reactive rather than proactive, leading to overstocking, understocking, or missed sales opportunities. Limited customer support and interaction has conventional e-commerce platforms that provide minimal assistance to customers. Users often struggle to find suitable products or obtain quick answers to queries, negatively impacting user experience and conver- sion rates. Operational inefficiency in system updates manual software deployment and testing processes increase development time and in- troduce a higher risk of errors, making it difficult to maintain system reliability and consistency. 1. 1. Problem Solution 1. Solution Architecture Overview The system follows a modular full-stack architecture in which intelligent backend services support decision-making while the frontend delivers a simple and responsive user experience. Machine learning models operate as decision-support components rather than autonomous controllers, ensuring that final business decisions remain under administrative supervision. 2. Core Solution Components AI-Assisted Pricing Engine: The system includes an AI-assisted pricing engine that generates price recommendations based on product type, purchase order quantity, customer region, predicted seasonal demand, and internally maintained competitor pricing data. The pricing engine functions as a decision-support system rather than a fully automated controller. All generated prices are forwarded to the administrator for review and approval before being published to customers, ensuring transparency and business control. Demand Forecasting Module: A machine learningbased demand forecasting module is integrated to predict future demand patterns using historical sales data along with regional and seasonal factors. The module is implemented using a Random Forest regression model and produces a demand index that supports pricing decisions and inventory planning. The predicted demand is used internally by the system and is not exposed to customers. Chatbot-Based Customer Assistance: An AI-powered chatbot is incorporated to assist customers with product-related queries, nav- igation, and basic order guidance. The chatbot uses a pretrained natural language processing model to understand user intent and provide relevant responses, improving customer engagement and reducing manual support requirements. Administrative Control and Approval Workflow: The system provides a dedicated administrative interface through which adminis- trators can manage products, review pricing recommendations, approve or modify prices, and monitor order activity. This workflow ensures centralized control over all critical business decisions. Technical Implementation Strategy Pricing Recommendation Pipeline: Pricing recommendations are generated using business-defined rules supported by demand fore- casting outputs and competitor pricing references. The pricing logic is implemented in the backend to maintain separation between user inteaction and business intelligence. Machine Learning Pipeline for Demand Forecasting: Historical sales data is preprocessed and used to train a Random Forest regres- sion model. The trained model predicts future demand, and its output is integrated into the pricing engine as a backend-only input. Chatbot Processing Pipeline: User queries are processed using a pretrained NLP model for intent understanding and response gen- eration. The chatbot logic is restricted to assistance and does not trigger direct system actions such as pricing changes or order confirmation. CI/CD Automation Support: CI/CD practices using GitHub Actions are employed to automate code integration, testing, and deploy- ment, improving development efficiency and system reliability without affecting runtime behavior. 3. Integration and Security Framework The proposed system integrates multiple external APIs and security mechanisms to ensure reliable and secure operation. Payment processing is handled through secure gateway services such as Razorpay or Stripe, enabling safe online transactions. For conversational assistance, chatbot processing utilizes pretrained natural language processing services accessed through OpenAI API or Hugging Face inference APIs to support intent understanding and response generation. Data persistence and management are implemented using MongoDB Atlas, a cloud-managed NoSQL database platform that provides scalability and flexible schema support. Security implementation within the system includes JWT-based authentication combined with role-based access control to ensure authorized access to administrative functionalities. All API communications are protected using HTTPS encryption, and sensitive information such as API keys and credentials is securely stored using environment variables to prevent unauthorized exposure. In addition, robust error handling and validation mechanisms are implemented across all integrated services to manage failures in payment processing, chatbot responses, machine learning predictions, and database operations, thereby maintaining system stability and providing reliable user feedback. 3. LITERATURE SURVEY Recent research highlights a growing adoption of artificial intelligence and machine learning techniques in e-commerce systems to overcome the limitations of static pricing, manual inventory management, and limited customer interaction. Traditional e-commerce platforms rely heavily on predefined pricing and reactive inventory strategies, which restrict their ability to respond to fluctuating demand and regional market conditions. To address these challenges, researchers have proposed intelligent systems that combine pricing automation, demand forecasting, and decision-support mechanisms. Dynamic and AI-assisted pricing has been widely studied as a method to improve revenue optimization and market competitiveness. Chen et al. [1] demonstrate that machine learningbased pricing models can generate adaptive price recommendations by analyzing order quantity, demand trends, and regional factors. Patel and Shah [3] further emphasize the importance of human-in-the-loop pricing systems, where AI provides recommendations while final pricing decisions remain under administrative control. This ap- proach improves transparency and reduces the risks associated with fully automated pricing systems, particularly for small and medium-scale enterprises. Demand forecasting plays a critical role in supporting pricing and inventory decisions. Kumar et al. [2] and Verma et al. [4] report that Random Forestbased regression models are effective in predicting seasonal and regional demand patterns using historical sales data. These studies highlight that accurate demand prediction enables businesses to anticipate future requirements and avoid over- stocking or stock shortages. Further advancements by Zhang et al. [11] and Wang et al. [18] show that integrating demand forecast- ing outputs directly into pricing and inventory systems improves overall operational efficiency and decision accuracy. Inventory management has also benefited from predictive analytics. Lee et al. [6] and Mehta et al. [14] present systems where forecast-driven inventory planning helps manufacturing and retail organizations optimize stock levels. Their findings suggest that combining demand prediction with administrative oversight results in more reliable and scalable inventory management solutions, particularly in sectors influenced by seasonal demand variations. Customer interaction in e-commerce platforms has evolved through the integration of conversational AI technologies. Das et al. [5], Adamopoulou et al. [13], and Kim and Park [19] discuss the use of chatbot-based systems to enhance customer engagement, provide real-time assistance, and simplify product navigation. These studies conclude that chatbots are most effective when deployed as support tools that assist users without directly executing transactional or pricing actions, thereby maintaining system reliability and trust. From a system development perspective, modern e-commerce platforms increasingly adopt full-stack web architectures and auto- mated deployment practices. Singh et al. [7] and Fernandez et al. [15] highlight the effectiveness of MERN-based architectures combined with CI/CD automation for building scalable and maintainable web applications. Brown et al. [8] further show that CI/CD pipelines using tools such as GitHub Actions reduce deployment errors and improve development efficiency without impacting runtime behavior. Overall, the reviewed literature indicates a clear trend toward intelligent, AI-assisted e-commerce systems that balance automation with human control. While existing studies address pricing optimization, demand forecasting, inventory management, and customer assistance independently, limited work focuses on integrating all these components within a single controlled architecture. The proposed Halchal E-Commerce Platform addresses this research gap by combining AI-assisted pricing, machine learningbased demand forecasting, chatbot-based customer support, and CI/CD-enabled development automation into a unified and business- controlled system. 4. ARCHITECTURE Fig. 1. Architecture of System. The system architecture of the proposed Halchal E-Commerce Platform is illustrated in Fig. 1. The architecture follows a modular full-stack design that integrates intelligent decision-support components with controlled business workflows. The system is struc- tured to separate user interaction, backend processing, AI-based services, administrative control, and data persistence, thereby en- suring scalability, security, and transparency. The frontend layer is developed using React.js and serves as the primary interface for both customers and administrators. Through this interface, users can browse products, manage carts, interact with the chatbot, and initiate order placement, while administrators can access dashboards for reviewing and approving pricing decisions. The frontend communicates with the backend using secure RESTful APIs. The backend layer, implemented using Node.js with Express.js, acts as the central controller of the system. It handles authentication, order processing, pricing requests, chatbot query routing, and communication with AI services and the database. All business rules and validations are enforced at this layer to maintain system consistency. The AI services layer includes two core components: demand forecasting and AI-assisted pricing. The demand forecasting module uses a Random Forest machine learning model to analyze historical sales data along with seasonal and regional factors. The predicted demand is generated in batch mode and passed as an internal input to the AI-assisted pricing module. The pricing module computes price recommendations based on product type, purchase quantity, customer reion, predicted seasonal demand, and internally main- tained competitor pricing data. These recommendations are not applied automatically. An administrative approval layer acts as a control mechanism between the pricing intelligence and data storage. All price recom- mendations generated by the AI-assisted pricing module are reviewed by an administrator. Prices are finalized only after explicit approval, ensuring transparency and preventing uncontrolled automated pricing. The system also integrates a chatbot service, implemented using a pretrained NLP model accessed via an external API. Customer queries are routed from the backend to the chatbot service, which returns contextual responses related to products and navigation. The chatbot operates strictly as a support component and does not perform transactional or pricing actions. The data layer uses MongoDB Atlas as a cloud-hosted NoSQL database to store user data, product information, orders, approved prices, competitor pricing references, and historical sales records. Payment transactions are processed securely through an external payment gateway such as Razorpay or Stripe, with transaction status updates handled by the backend. Additionally, CI/CD pipelines implemented using GitHub Actions support automated build, testing, and deployment processes. These pipelines improve development efficiency and deployment reliability but do not affect the runtime behavior of the system. Overall, the proposed architecture effectively combines AI-assisted pricing, machine learningbased demand forecasting, chatbot- based customer assistance, and administrative control within a single unified framework, making it suitable for both academic evaluation and real-world deployment. 5. IMPLEMENTATION DETAILS The implementation of the proposed Halchal E-Commerce Platform is organised into multiple interconnected modules designed to support intelligent pricing, demand forecasting, administrative control, customer interaction, and secure transaction management. The AI-assisted pricing module generates price recommendations by analysing product type, purchase quantity, customer region, predicted seasonal demand, and internally maintained competitor pricing data. The generated prices are not directly published to customers; instead, they remain in a pending state until administrative approval is completed. This human-in-the-loop mechanism ensures controlled automation while maintaining transparency and business oversight. The demand forecasting module is implemented using a Random Forest regression model that analyses historical sales data, seasonal indicators, and regional demand patterns to predict future demand trends. The forecasting process operates in batch mode and pro- duces a demand index that supports pricing decisions and inventory planning. Since forecast accuracy depends on the availability and quality of historical datasets, the module is designed as a decision-support system rather than a fully automated controller. The administrative approval module is incorporated to enable administrators to review, approve, or modify AI-generated price recommendations before publication. This module is integrated within the administrative dashboard and enforces a strict manual approval workflow, ensuring that all finalised prices align with business policies. A chatbot assistance module is integrated into the platform to improve customer interaction. The chatbot utilizes a pretrained natural language processing model accessed through an external API to assist users with product-related queries, navigation guidance, and frequently asked questions. The chatbot operates strictly as an informational support component and does not execute transactional or pricing actions. The order and payment module manages order placement, payment processing, and transaction status tracking through secure pay- ment gateway integrations such as Razorpay or Stripe. The system ensures secure communication and reliable transaction handling, contributing to a high transaction success rate. Furthermore, an inventory support module leverages forecasted demand insights to assist administrators in seasonal stock planning and inventory awareness. This module functions as a non-automated decision-sup- port tool, allowing administrators to make informed inventory adjustments. The backend framework of the system is implemented using Node.js with Express.js to develop modular RESTful APIs that handle authentication, product management, pricing logic, forecasting access, chatbot routing, and order processing. The lightweight server configuration ensures scalability and suitability for academic as well as prototype deployments. On the frontend, the platform utilizes HTML5, CSS3 with Bootstrap 5, JavaScript (ES6), and React.js to create a responsive single-page application interface. The ad- ministrative dashboard provides visual access to pending price recommendations, approved prices, inventory indicators, and order summaries, enabling efficient administrative control. Core interface components include product listing and cart management, checkout and order tracking pages, chatbot interaction panels, and administrative tools for pricing approval and product manage- ment. The backend framework of the proposed system is implemented using Node.js with Express.js to develop RESTful APIs that manage authentication, product management, pricing logic, forecasting access, chatbot routing, and order processing. The server configura- tion follows a lightweight architecture suitable for academic and prototype deployment while maintaining scalability and modular- ity. The API design adopts a structured approach that separates business logic from user interaction, ensuring secure communication and efficient data processing across all integrated services. The frontend interface of the platform is developed using HTML5, CSS3 with Bootstrap 5, and JavaScript (ES6), with React.js used to implement a responsive single-page application architecture. The user interface supports dynamic chatbot interaction, product browsing, and order tracking while providing administrators with a dashboard to review pending price recommendations, approved prices, inventory indicators, and order summaries. Core interface components include product listing and cart management, checkout and order tracking pages, chatbot UI integration, and an administrative dashboard designed for pricing approval, product manage- ment, and demand overview visualization through RESTful API communication. The machine learning implementation within the proposed system focuses on demand forecasting using a Random Forest regression model developed with the scikit-learn library. The model is trained using historical sales data and incorporates multiple input fea- tures including product type, customer region, historical sales quantity, and seasonal indicators to capture demand variations across time and geography. The forecasting process operates periodically in batch mode and produces a predicted demand index that is utilized internally for pricing recommendations and inventory planning support. The generated forecast values are not exposed directly to customers; instead, they function as backend decision-support inputs that enhance system intelligence while maintaining administrative control over business operations. The forecasting model was evaluated using historical validation data to ensure reliable demand prediction accuracy. The AI-assisted pricing logic integrates multiple pricing inputs such as base product price, purchase quantity, customer region, predicted seasonal demand, and competitor pricing references maintained by administrators. Based on these factors, the pricing engine generates dynamic price recommendations that support informed decision-making while preserving business transparency. The system operates under a human-in-the-loop framework in which generated prices remain in a pending state until reviewed and approved by an adminisrator. This approach ensures fairness, pricing consistency, and compliance with organizational policies while preventing fully automated pricing decisions from being applied without supervision. The chatbot processing module utilizes a pretrained natural language processing model accessed through external APIs such as OpenAI API or Hugging Face Inference API to support intelligent user interaction. The chatbot is designed to assist users with product-related information queries, navigation guidance, and responses to frequently asked questions, thereby improving customer engagement and usability within the platform. The operational scope of the chatbot is limited to informational assistance, and it does not execute transactional operations, pricing modifications, or administrative actions. This controlled design ensures that au- tomated responses enhance user experience while maintaining strict system security and administrative governance. The data storage architecture of the system is implemented using MongoDB Atlas, a cloud-hosted NoSQL database that provides scalability, flexible schema design, and seamless integration with the Node.js backend. The database maintains multiple collections including user and role information, product data, order and payment status records, approved pricing details, competitor pricing references, and historical sales datasets used for demand forecasting. MongoDB is selected to support dynamic data structures and efficient query performance, enabling reliable storage management and facilitating smooth communication between machine learn- ing components, backend services, and administrative dashboards. The system incorporates multiple security and authentication mechanisms to ensure safe access and data protection across all plat- form components. User and administrator authentication is implemented using JWT-based authorization combined with role-based access control to restrict sensitive administrative operations. All API communications are secured through HTTPS encryption to prevent unauthorized data interception during transmission. Additionally, sensitive credentials such as API keys and configuration secrets are securely stored using environment variables, ensuring compliance with secure development practices and protecting critical system resources from exposure. The platform integrates CI/CD automation using GitHub Actions to streamline development, testing, and deployment processes. The continuous integration pipeline manages code integration and automated checks to maintain code quality and detect potential issues early in the development lifecycle. Following successful validation, the deployment stage enables seamless application up- dates while minimizing downtime and maintaining system stability. This automated workflow enhances development efficiency, ensures consistent software delivery, and supports reliable deployment practices aligned with modern DevOps methodologies. Fig. 2. Admin Dashboard 6. CONCLUSION This paper presented an AI-enabled e-commerce platform for Halchal Industries that integrates AI-assisted pricing, machine learn- ing-based demand forecasting, chatbot support, and CI/CD automation within a unified full-stack architecture. The proposed system generates intelligent pricing recommendations based on purchase quantity, regional factors, and seasonal demand while maintaining administrative control through a mandatory approval workflow. The Random Forest-based forecasting model supports informed pricing and inventory planning, and the chatbot enhances customer interaction without executing transactional operations. The overall architecture demonstrates a scalable and practical approach to integrating artificial intelligence with controlled business workflows, making it suitable for real-world deployment as well as academic evaluation. Future work may include real-time adaptive pricing using reinforcement learning and live demand-stream integration. REFERENCES 1. Machine LearningBased Dynamic Pricing Models for E-Commerce Platforms Chen et al., 2023 2. Demand Forecasting Using Random Forest for Retail and Manufacturing Systems Kumar et al., 2023 3. AI-Assisted Pricing Systems with Human-in-the-Loop Control Patel and Shah, 2023 4. Seasonal Demand Prediction for Inventory Optimization Using Machine Learning Verma et al., 2023 5. Chatbot-Driven Customer Engagement in E-Commerce Applications Das et al., 2023 6. Intelligent Inventory Management Using Predictive Analytics Lee et al., 2023 7. Secure and Scalable E-Commerce Platforms Using MERN Stack Singh et al., 2023 8. CI/CD Automation for Web Applications Using GitHub Actions Brown et al., 2023 9. Machine Learning Models for Sales Forecasting in Online Markets Taylor and Wilson, 2023 10. Ethics and Transparency in Algorithmic Pricing Systems Ezrachi et al., 2023 11. AI-Driven Demand Forecasting for Supply Chain Optimization Zhang et al., 2024 12. Decision-Support Pricing Systems Using Machine Learning Roberts and Lee, 2024 13. Conversational AI Chatbots for Online Retail Platforms Adamopoulou et al., 2024 14. Predictive Analytics for Inventory Planning in Manufacturing Industries Mehta et al., 2024 15. Cloud-Based E-Commerce Systems with Automated Deployment Pipelines Fernandez et al., 2024 16. Human-Centered AI for Business Decision-Making Systems Rahwan et al., 2024 17. Machine LearningEnabled Pricing Optimization for SMEs Oliveira et al., 2024 18. Demand Forecasting and Pricing Integration in Smart Commerce Systems Wang et al., 2025 19. AI-Assisted E-Commerce Platforms with Chatbot Integration Kim and Park, 2025 20. Automated Pricing and Inventory Control Using Predictive Models Gupta et al., 2025 ______________

Halchal E-Commerce Platform with CI/CD Pipeline and Automated Pricing System View Abstract & download full text of Halchal E-Commerce Platform with CI/CD Pipeline and Automated Pricing System D...

#Volume #15, #Issue #02 #(February #2026)

Origin | Interest | Match

0 0 0 0
🇨 🇭 🇪 🇷 🇾 🇱 🇺🇸 🇨🇦 🇺🇦 🩵 💙 🌊
🇨 🇭 🇪 🇷 🇾 🇱 🇺🇸 🇨🇦 🇺🇦 🩵 💙 🌊
@confettimother.bsky.social
1 week ago
Silhouetted crowd holding signs, illustrating a protest. Text reads, "The purpose of protest is to provoke a response..." by Jeffrey G. Duarte. Tone: Reflective.

Silhouetted crowd holding signs, illustrating a protest. Text reads, "The purpose of protest is to provoke a response..." by Jeffrey G. Duarte. Tone: Reflective.

"The purpose of #protest 🪧 is to provoke a response. Trouble is some #people prefer to address the appropriateness of the protest not the #issue." ― Jeffrey G. Duarte

#QuoteSky #Resistance 🌊

1 0 0 0
Transplant International
Transplant International
@transpl-int.bsky.social
1 week ago
Video thumbnail

THE JANUARY ISSUE IS ONLINE!!

"Simultaneous pancreas-kidney transplantation under scrutiny”

Check it out here: shorturl.at/QUZYy

#january #issue #cover #pancreas #kidney #transplant @esottransplant.bsky.social

1 0 0 0