Thursday
Room 6 - OWASP
10:20 - 11:20
(UTC+01)
Talk (60 min)
Breaking the Black Box: Why Testing Generative AI Is Full Spectrum
Forget the black and white world of traditional Red Teaming, where success means finding that one perfect exploit. In the age of GenAI, we're painting with a whole new palette. When your target can think, reason, and never give the same answer twice, how do you know if you've really broken it?
Welcome to the technicolor challenge of AI Red Teaming, where we're not just looking for vulnerabilities - we're evaluating personality quirks, safety boundaries, and whether an AI system has gone rogue in fascinating new ways. Join me to explore why it takes AI to test AI, how the future of Red Teaming is less binary, and even your testing tools need to think outside the (black) box.
Jason Ross
Jason Ross is a passionate cybersecurity expert with a diverse skill set in generative AI, Penetration Testing, Cloud Security, and OSINT. As a product security principal at Salesforce, Jason performs security testing and exploit development with a specific focus on generative AI, Large Language Models, and Agentic systems.
Jason is a frequent speaker at industry conferences, and is active in the security community: participating as a core member of the OWASP Generative AI Security Project, Co-Lead of the OWASP GenAI Red Team Initiative, and serving as a DEF CON NFO goon.