Travis Smith

WORKSHOP: The AI-talian Job: Hands-on attacks on AI Systems

Want to attack AI but not sure how? We’ll teach you how to hack realistic AI-enabled systems to exploit them for your own gain. In this workshop, you’ll attack the models of a major fictional financial institution – HiddenBank, and exploit its RAG-enabled LLM to extract sensitive data about its operations. Using what you’ve stolen, you’ll give Catch Me If You Can a run for its money and forge checks that you might (not) be able to cash. You’ll learn how organizations are implementing AI in business-critical settings and discover methods for attacking both generative and predictive AI alongside best practices for mitigation.

Travis Smith is Vice President of ML Threat Operations at HiddenLayer where he is responsible for the services offered by the organization, including red-teaming machine learning systems and teaching adversarial machine learning courses. He has spent the last 20 years building enterprise security products and leading world class security research teams. Travis has presented his original research at information security conferences around the world including Black Hat, RSA Conference, SecTor, and DEF CON Villages.