Designing and Participating in AI Bug Bounty Programs
Dane Sherrets, Shlomie Liberow
DEF CON 33 · Day 1 · Main Stage
This talk, originally titled "Securing Intelligence: How Hackers are Breaking Modern AI Systems and How Bug Bounty Programs Can Keep Up," delves into the cutting-edge intersection of artificial intelligence and cybersecurity. Presented by seasoned bug bounty hunters Dane Sherrets and Shlomie Liberow, the session offers a dual perspective: guiding hackers on effective techniques to identify vulnerabilities in AI systems and providing program managers with actionable strategies to mitigate these emerging risks through well-structured bug bounty initiatives.
AI review
Competent, practitioner-level coverage of AI bug bounty mechanics with real engagement stories and concrete lessons — but it's fundamentally a well-told experience report, not novel research. The technical cases are genuine and instructive; the insights don't move the field forward in any meaningful way.