Agents Are Powertools
I want to explain why I think the security industry is going a bit too all in on AI to those who are unfamiliar with the topic. From the outside...
Blog
Research insights, event recaps, and perspectives on AI security from our community.
Hacking AI Browsers: How i hacked Perplexity
I Hacked Perplexity and found: template injection, highlight injection, and chat-based data exfiltration. Here’s the story.
AI Village Announcing Generative Red Team 3 at DEF CON 33
The GRT 3 will run online in about a month with partners. Please sign up here https://auth.aivillage.org/login to recieve an email with more information. In 2023, AI Village organized the...
The Moat for AI
The value of AI companies is largely the security layers they provide.
AI Village Announcing Generative Red Team 2 at DEF CON 32
At DEF CON 31 AI Village hosted the Generative Red Team GRT1 , the world’s largest, public Large Language Model LLM Red Team, in conjunction with other non profit, corporate,...
Generative Red Team Recap
Generative Red Team History It’s long overdue for a retrospective on the Generative Red Team GRT at AI Village at DEFCON 31. I’ve posted parts of this other places, but...
Threat Modeling LLM Applications
Before we get started: Hi My name is GTKlondike, and these are my opinions as a cybersecurity consultant. While experts from the AI Village provided input, I will always welcome...
AI Village at DEF CON announces largest-ever public Generative AI Red Team
Largest annual hacker convention to host thousands to find bugs in large language models built by Anthropic, Google, Hugging Face, NVIDIA, OpenAI, and Stability. This event is supported by the...
The Spherical Cow of ML Security
First of all, these are my opinions and there are people at AI Village who may disagree with me. I want to present the simplest version of managing risk of...
Prompt Detective at SXSW!
Prompt Detective Announcement Join us for an upcoming workshop on the benefits and limitations of large language models LLMs like GPT3, Bloom, , and a unique red teaming exercise where...
The AI RMF Does not Address Common Needs
Disclaimer: This does not reflect the AIV as a whole, these are my opinions and this was my response. I believe that the Risk Management Framework is lacking in actionable...
The Use of AI/ML in Offensive Security Operations
The Red Team Village https://redteamvillage.io/ and the AI Village will host a panel from different industry experts to discuss the use of artificial intelligence and machine learning in offensive security...
AI and Hiring Tech Panel
AI and ML is already being used to identify job candidates, screen resumes, assess worker productivity and even help tag candidates for firing. Can the interview chatbot AI really be...
DEFCON 30 Friday Schedule
Automate Detection with Machine Learning Time : 9:30 11:00 \ Speaker : Gavin Klondike Today, over a quarter of security products for detection have some form of machine learning built...
DEFCON 30 Saturday Schedule
A few useful things to know about AI Red Teams Time : 10:00 11:00 \ Speaker : Sudipto Rakshit AI Red Teams are sprouting across organizations: Microsoft, Facebook, Google, DeepMind,...
DEFCON 30 Sunday Schedule
Automate Detection with Machine Learning Time : 9:00 10:30 \ Speaker : Gavin Klondike Today, over a quarter of security products for detection have some form of machine learning built...
Generative Art
Generative Art at AI Village DEF CON 30 Today, models that appear to generate novel outputs conditioned on text are becoming the mainstay of popular culture. New groups of users...
Gradient Attacks
Welcome to the second post in the AI Village's adversarial machine learning series. This one will cover the greedy fast methods that are most commonly used. We will explain what...
Max evil MLsec, why should you care?
Originally posted on Medium https://medium.com/@sarajayneterp/max evil mlsec why should you care ae3a42bfea52 follow @sarajayneterp https://medium.com/@sarajayneterp and like her article there MLsec is the intersection of machine learning, artificial intelligence, deep...
Dimensionality and Adversarial Examples
Welcome to AI Village’s series on adversarial examples. This will focus on image classification attacks as they are simpler to work with and this series is meant to explain the...
📝 Want to Contribute?
We welcome guest posts from the community! Topics we're interested in:
- AI security research and findings
- Tool releases and tutorials
- Event recaps and conference reports
- Opinion pieces on AI ethics and policy
- Technical deep dives and case studies
Submit a pull request → or reach out on Discord to discuss your ideas.