threlfall's Avatar

threlfall

@threlfall

offsec engineer @ Dropbox https://5stars217.github.io https://wiki.offsecml.com

391
Followers
61
Following
10
Posts
27.10.2024
Joined
Posts Following

Latest posts by threlfall @threlfall

Home | CackalackyCon

15 days to get your CFP in for Cackalackycon!

If you are somewhat knowledgeable in any interesting field of hacking, technology, robotics, science, global thermonuclear war, lock circumvention, etc. (but mostly hacking), we cordially invite you to submit your proposal.

www.cackalackycon.org

30.01.2026 23:13 ๐Ÿ‘ 1 ๐Ÿ” 1 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Preview
Offensive AI Conference | Join us in Oceanside, San Diego Welcome to OAIC. The world's first, invite-only Offensive AI Conference in Oceanside, San Diego, CA.

Looking forward to this event in October.

www.offensiveaicon.com

Hope to see you there?

20.03.2025 12:26 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Preview
CackalackyCon: Call for Papers Greetz to all h4x0rs, stuff-breakers, InfoSec pros, g33k girls, international spies, and script kidz,CackalackyCon will occur on May 16-18, 2025 in R...

This Friday is the last day to get your #CFP in for the 2025 conference! Don't miss out on sharing your knowledge.

sessionize.com/cacka...

10.02.2025 17:15 ๐Ÿ‘ 0 ๐Ÿ” 1 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 1
Preview
Senior Machine Learning Engineer, Strategic Intelligence Group

Dropbox is looking for a senior ML engineer to join our threat intelligence and product trust & safety team. DM me if you want to know more

jobs.dropbox.com/listing/6556...

28.01.2025 13:37 ๐Ÿ‘ 2 ๐Ÿ” 1 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
CackalackyCon

Have you been to @cackalackycon.bsky.social? I'd encourage you to check it out, and submit a talk. CkC is an old-school hacker con w/no sponsors. Anything from tech talks to wild hacker adjacent topics are fair game! CFP closes on Valentines Day. Will you be our valentine? ๐Ÿซ€https://cackalackycon.org

15.01.2025 17:19 ๐Ÿ‘ 2 ๐Ÿ” 1 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Preview
Stats and Bytes | Josh Collyer | Substack Keeping you up to date with where AI and Security collide. Click to read Stats and Bytes, by Josh Collyer, a Substack publication. Launched 2 days ago.

The first issue of Top 5 Security and AI Reads at statsandbytes.fyi is cut and scheduled. Excited to see how it's received! ๐Ÿซฃ What's the worst that can happen!?

04.01.2025 16:19 ๐Ÿ‘ 3 ๐Ÿ” 2 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0
Preview
CackalackyCon: Call for Papers Greetz to all h4x0rs, stuff-breakers, InfoSec pros, g33k girls, international spies, and script kidz,CackalackyCon will occur on May 16-18, 2025 in R...

What's that? A wild #CFP Appears? Our CFP for 2025 is open! We're so excited to see what you're offering to share with everyone. Be sure to read and follow the guidelines.

sessionize.com/cacka...

#infosec #conference #cybersecurity

16.12.2024 14:00 ๐Ÿ‘ 0 ๐Ÿ” 2 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

That keynote was my favorite too, really great reflection

18.11.2024 18:44 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
A very cute old stone house nestled in the woods in Ireland

A very cute old stone house nestled in the woods in Ireland

Visiting Ireland. Iโ€™m pretty sure I am supposed to be living here next to a Neolithic magic site but my ancestors were deported to Australia

15.11.2024 19:29 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0

bsky.app/profile/heid...

12.11.2024 14:30 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 1 ๐Ÿ“Œ 0
Video thumbnail

Man the saltburn liquid vinyl what possessed me lmao

09.11.2024 16:38 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Windows Agent Arena: Evaluating Multi-modal OS Agents at Scale Windows Agent Arena (WAA) is a scalable Windows AI agent platform for testing and benchmarking multi-modal, desktop AI agents. WAA provides researchers and developers with a reproducible and realistic...

we also introduce a new multi-modal agent, Navi, showing it can achieve a success rate of 19.5%, compared to 74.5% for human performance. microsoft.github.io/WindowsAgent...

04.11.2024 13:11 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Post image

Toctuah

27.10.2024 14:11 ๐Ÿ‘ 0 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0
Welcome to the Offensive ML Playbook - OffSecML Playbook Welcome to the Offensive ML Playbook - OffSecML Playbook

I just added a bunch more works to wiki.offsecml.com, and I mapped (almost) all current items to MITRE Altas.

I think my favorite new addition is this:

Detecting deviations in meaning trajectories to defend LLMs, which seems really interesting and promising!

27.10.2024 14:05 ๐Ÿ‘ 1 ๐Ÿ” 0 ๐Ÿ’ฌ 0 ๐Ÿ“Œ 0