A Developer in OpenAI's Private Bug Bounty 🤓 🛡️ 🤖
summary
A developer who builds chatbots for millions of travelers describes how experimenting with ChatGPT led to a temporary ban and later acceptance into OpenAI’s private Bug Bounty program. The talk explains why a developer should adopt an attacker’s mindset to test and secure AI Agents, and shares lessons for thinking outside normal usage to better own and protect future AI deployments.
AI-written summary · about
chapters (10)
- 0:00Bug bounty journey
- 1:03AI security workshop prep
- 2:28Jailbreak experience
- 3:30Private bounty discovery
- 4:59Program selection
- 5:42AI security resources
- 7:55Jailbreak tools & attacks
- 10:01Bug bounty results
- 11:25Self Red Teaming benefits
- 13:29Workshop & conclusion
related talks
18mDefending the unknown using AI and cybersecurity
37mHow to Break AI Systems (Before Someone Else Does)
01h 24mOffensive Cybersecurity by AI Promises and Pitfalls
53mHow to Break AI Systems (Before Someone Else Does)
26mChallenging the Boundaries of Pentesting — The Age of AI
25mPreventing an OWASP Top 10 in the world of AI
54mA Practical Guide to AI Threats & Mitigation Strategies
36mHow NOT to Train Your Hack Bot: Dos and Don'ts of Building Offensive GPTs