Hacking neural networks so that we don’t get stuck in the matrix. Red Team Director @ Electronic Arts. Entrepreneur. Builder and Breaker. Opinions are my own.embracethered.com 127.0.0.1Joined February 2012
Great news! 📰
The Google Labs team reached out to me directly, and a fix for the image based data exfiltration vulnerability in NotebookLM has been deployed last night!
👍
Great news! 📰
The Google Labs team reached out to me directly, and a fix for the image based data exfiltration vulnerability in NotebookLM has been deployed last night!
👍
Had a great time talking about LLM security, threats and mitigations at BSides San Diego! @BsidesSD
Thanks for coming by and shout out to organizers and volunteers for putting together the event.
#bsides#llm#infosec#ml
Just wrapped up my Prompt Injection and LLM security talk at #hackspacecon 🚀🚀🚀
Thanks for coming by and shout out to organizers & volunteers for helping make it such an excellent event. 👍
Also, fantastic location! 🛰️ 🙂
Homefield Advantage!
Today marks four years that my book about building and managing an internal Red Team was published. 📖 🎉
Still bummed I couldn't do an irl book tour back then, but very grateful for all the reviews and that it seems to be useful 🙏🙂…
Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks 🌶️
"we show that it is possible to conceptualize the creation of execution triggers as a differentiable search problem and use learning-based methods to autonomously generate them."
"Our…
AI has resurrected the discipline of software testing. Finally, a reason to think hard about testing once again. If you want to join me for an AI-focused test meetup in Kirkland WA, dm your email address.
And read this: medium.com/@docjamesw/the…
Reading a tweet is a bit like downloading an (attacker-controlled) executable that you instantly run on your brain. Each one elicits emotions, suggests knowledge, nudges world-view.
In the future it might feel surprising that we allowed direct, untrusted information to brain.
👉 Indirect Prompt Injection =>
Remote Neuron Activation
It's sort of the LLM equivalent of RCE in traditional computers.
In other words, an attacker just has to tickle the right neurons to strongly influence (and often entirely control) the output of the computation.
Imagine you are a Microsoft SQL Server...
Having fun redoing some of my ChatGPT experiments with Claude.
Switching DBs, creating and querying tables, etc all works very well.
Also, it thinks it runs as local system.
#sqlserver#claude#llm
Great to see the Claude 3 system prompt being explained in detail by Anthropic!
Hopefully this sets a new industry best practice!
Great job! @AmandaAskell
Great to see the Claude 3 system prompt being explained in detail by Anthropic!
Hopefully this sets a new industry best practice!
Great job! @AmandaAskell
25K Followers 6K FollowingAssociate Professor @ NYU Tandon. Security, RE, ML. PGP https://t.co/3WXr0RfRkv
Founder of the MESS Lab: https://t.co/zGycrX3Gmn
"an orc smiling into the camera" — CLIP
140K Followers 922 FollowingAI · SECURITY · MEANING → HUMAN 3.0 ⚒️Founder of UL, Creator of Fabric & Threshold 👤Human 2.0: 🟩🟩⬛️⬛️⬛️ Human 3.0 📋Apple, Robinhood, IOActive, HP, Army
24K Followers 25K FollowingA Hacker who is A Lover of People, and Life @RetroTwinz @Secbsd, @GrumpyHackers, @NovaHackers, @deadpixelsec @hacknotcrime Advocate @PositivelyBlue_ OSCP, OSWP
22 Followers 54 Followingshe/her. AppSec Engineer. International Speaker. Occasional blogger. Choose happiness. Making security less daunting with a smile ;) Opinions my own.
13K Followers 1K FollowingML Engineer (e/acc)
📌 https://t.co/x0IIWfnOt8
🚀 https://t.co/QEO4CKRl1b
Open LLMs is Happiness 💡
Ex Deutsche & HSBC.
DM for collaboration.
504K Followers 68K FollowingFollow me on my new podcast with AI startups, Unaligned. Tech industry color commentator since 1993. Author/Blogger. Former strategist @Microsoft.
27K Followers 203 FollowingFollow me for Cybersecurity #Thought #Leadership.
Director Red Team.
Help organizations safeguard their businesses from the bad guys.
92K Followers 123 FollowingA portable multi-tool device in a toy-like body for pentesters and hardware geeks. Buy worldwide here ➡️ https://t.co/n09EKVnqri
184K Followers 1K FollowingDirector of Cybersecurity @EFF / Co-founder of @stopstalkerware/ My tweets are my own, not my employers’ / I did a TED talk once /
17K Followers 2K FollowingPrincipal Identity Security Researcher at Microsoft. Ex-Secureworks. (MSc, MEng, PhD, CITP, CCSK).
And yes, opinions are my own ;)
140K Followers 922 FollowingAI · SECURITY · MEANING → HUMAN 3.0 ⚒️Founder of UL, Creator of Fabric & Threshold 👤Human 2.0: 🟩🟩⬛️⬛️⬛️ Human 3.0 📋Apple, Robinhood, IOActive, HP, Army
24K Followers 25K FollowingA Hacker who is A Lover of People, and Life @RetroTwinz @Secbsd, @GrumpyHackers, @NovaHackers, @deadpixelsec @hacknotcrime Advocate @PositivelyBlue_ OSCP, OSWP
2K Followers 438 FollowingFounder of @census. Building modern ops on top of your data warehouse. Prev. founder of Meldium (acq. by LogMeIn). YC & MS alum. Amateur tour guide.
979K Followers 905 Following🧑🍳. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets 🧠🤖💥
8K Followers 43 FollowingThe first place over 50k AI Engineers gather to talk models, tools and ideas. Breaking news today you will use at work tomorrow!
Hosted by @swyx and @fanahova
8K Followers 311 FollowingVP of Engineering at Google, working on basic problems and applications in AI, with a focus on privacy.
Order my book 'Who Are We Now?' out now ⬇️
432 Followers 1K FollowingI help make the world a more secure place @msftsecurity - @BSidesVI cat herder - Views are 100% mine - #dodgers & #bluejays - he/him
3K Followers 477 FollowingSenior Threat Researcher @TXOneNetworks. Speaker at Black Hat USA,CODE BLUE, DEFCON, HITB, HITCON, VXCON, ROOTCON. Author of Windows APT Warfare
3K Followers 948 FollowingResearcher / Co-Founder @TrapaSecurity & @pwnabletw/ MSRC Top 100 2019/2020 / Focus on hunting bugs that are as useless as me / @[email protected]
478 Followers 263 FollowingWeb Security Researcher @starlabs_sg | Patience is a virtue. Every puzzle has an answer. | Opinions expressed are of my own.
3K Followers 703 FollowingUsing bad guys to catch math since 2010. Principal Security Architect (AI/ML) at NVIDIA. He/him. Personal account and opinions: `from std_disclaimers import *`.
3K Followers 2K FollowingSecurity Data Cowboy @Azure. Yes, the job is as cool as it sounds. Tech Policy Fellow @UCBerkeley. @BKCHarvard Affiliate. https://t.co/eph3QDsIGB
403 Followers 560 FollowingHusband, father, Identity/Security guy, Islay enthusiast. Passionate about the passwordless future with #FIDO2 and #WebAuthn.
679K Followers 753 FollowingFounder of Lyn Alden Investment Strategy. Finance+engineering background. GP @egodeathcapital. BoD at https://t.co/FHNz9MBftH (where I buy my bitcoin).
No recent Favorites. New Favorites will appear here.