Security News > 2023 > August > DEF CON Generative AI Hacking Challenge Explored Cutting Edge of Security Vulnerabilities

Data from the human vs. machine challenge could provide a framework for government and enterprise policies around generative AI. OpenAI, Google, Meta and more companies put their large language models to the test on the weekend of August 12 at the DEF CON hacker conference in Las Vegas.
The Generative Red Team Challenge organized by AI Village, SeedAI and Humane Intelligence gives a clearer picture than ever before of how generative AI can be misused and what methods might need to be put in place to secure it.
Generative Red Team Challenge could influence AI security policy.
The Generative Red Team Challenge asked hackers to force generative AI to do exactly what it isn't supposed to do: provide personal or dangerous information.
The AI Village team will use the results of the challenge to make a presentation to the United Nations next month, Rumman Chowdhury, co-founder of Humane Intelligence, an AI policy and consulting firm, and one of the organizers of the AI Village, told Axios.
"For many who are deploying LLM systems, there are a lot of security practices that exist today under the cloud and cloud-based security that can be immediately applied to LLMs that in some cases have been skipped in the race to get to LLM deployment. Don't skip those steps. We all know how to do cloud. Take those fundamental precautions to insulate your LLM systems, and you'll go a long way to meeting a number of the usual challenges."
News URL
https://www.techrepublic.com/article/def-con-hackers-generative-ai/
Related news
- Taiwan Bans DeepSeek AI Over National Security Concerns, Citing Data Leakage Risks (source)
- Cyber agencies share security guidance for network edge devices (source)
- On Generative AI Security (source)
- Microsoft Edge update adds AI-powered Scareware Blocker (source)
- Zimbra Releases Security Updates for SQL Injection, Stored XSS, and SSRF Vulnerabilities (source)
- AI and Security - A New Puzzle to Figure Out (source)
- Google Chrome's AI-powered security feature rolls out to everyone (source)
- CrowdStrike Security Report: Generative AI Powers Social Engineering Attacks (source)
- Innovation vs. security: Managing shadow AI risks (source)
- Google's March 2025 Android Security Update Fixes Two Actively Exploited Vulnerabilities (source)