As AI systems become more deeply embedded in our critical infrastructure, the need for advanced security practices is urgent. In this featured talk, Brett Ewing explores the emerging field of ethical AI hacking and how red and blue teaming practices are evolving to meet the unique challenges of machine learning, generative AI, and autonomous systems. This session will offer practical insights into how organizations can simulate attacks on AI systems, defend against model manipulation, and build more secure and resilient AI pipelines. Whether you're a security pro, policy advisor, or AI developer, you'll leave with a better understanding of how to pressure test and harden AI systems before attackers do.
