This 4-hour technical session helps security leaders & practioners understand how modern AI systems fail and how to secure them. It covers prompt injection, jailbreaks, agent abuse, and the critical differences between model, application, and infrastructure risk. Through threat modeling, focused hands-on exercises, and practical enterprise examples, participants will learn how to assess AI applications and agents, identify control gaps, and build a pragmatic AI security program.

* Please note: This is not included in the Main Conference registration and requires a separate registration.