1) Ok, now that I have a moment I wanna tell some of the story behind this event at @aivillage_dc as I've been working on this for 9 months.

This, but for AI Security. The field is filled with people trying to make a quick buck and don't care about the long term health of the field and it's community.

I'll be at @RealAAAI Conference in Philadelphia this week, where I am part of two accepted papers: 1. Quantifying Misalignment Between Agents: Towards a Sociotechnical Understanding of Alignment, with @AidanKierans , Hananel Hazan, and @ShirKi . In this work, we introduce a novel mathematical model to measure misalignment between multiple human and AI agents across various problem domains, moving beyond single-agent or monolithic approaches to alignment. Through simulations and case studies we demonstrate how our model captures nuanced aspects of misalignment in complex sociotechnical environments, providing enhanced explanatory power for real-world scenarios where agents may hold conflicting goals. Come see our poster during the AI Alignment Track on Friday the 28th - 12:30pm! 2. To Err is AI: A Case Study Informing LLM Flaw Reporting Practices, with @seanmcgregor , @ShayneRedford, @comathematician, and others! This paper documents lessons learned from a bug bounty event at DEF CON 2024 where 495 hackers tested the Open Language Model (OLMo) for flaws, revealing challenges in AI safety reporting processes. Through real-time adjudication of 200 submissions, we identify key insights for effective flaw reporting programs, including the need for specialized tooling, clear documentation practices, and proper adjudication expertise, demonstrating how systematic evaluation and coordinated, structured flaw reporting of AI systems can help prevent real-world harms. See this work presented at IAAI in the "AI Safety, Reliability, and Incident Management" session on Thursday the 27th at 2:30pm! If you're around and want to chat, hit me up! Let's talk AI, Disclosures, Agents, and more!

i broke deepseek

I got hopeful that the ML attack, Hop Skip Jump, was in the wild...

Coding in python feels like spooky action at a distance. You never quite know what you're doing and the documentation is mostly there.

I've been in the US for 20 years. We landed 9/11/2004.

We dunked them this year. #dunkafed @BlueTeamVillage @aivillage_dc @wisporg @BlackInCyberCo1

Reminder Alert* The #BiohackingVillage is proud to be a #CNA (#CVE Numbering Authority), empowering us to assist companies in managing and disclosing #vulnerabilities responsibly. More info at villageb.io/cna. #VulnerabilityDisclosure #Cybersecurity #PatientSafety

One way to make a QM goon happy is to give them gaffer tape and power strips. AIV had some extra. 😄

We built a quick landing page in @wix and every part of their site is designed to take your domain hostage. Never use them. #enshittfication

This year's AIV is what I want @aivillage_dc at @defcon to be. Community, connections, and learning is what I want to foster.

@dreadnode and @bugcrowd built the platform. @allen_ai and UL's DSRI brought the model. @AISafetyInst and @GoogleAI made the workshop happen. There were a bunch of other people and orgs that helped plan and execute.

A special shout out to Emily McReynolds who just showed up for her first DEFCON and just helped. She was amazing.

Generative Red Team 2 was a massive success. We paid $7350 in bounties. We learnt so much about bounties and reporting for ML. Thank you to everyone who participated!! (specific acks in the thread below)

I just wanted to take a nap and couldn't figure out why my key wasn't working. I went down 4 times to get new keys until security was called to check out my door. That's when I was told I was put on a special list, and my door permanently locked.