2025-10-25 –, Talk 2
This talk explores the converging risk factors that could transform helpful AI systems into potential security threats within organizations. We examine three critical ingredients that create this vulnerability: increasing capability, expanding agency, and exploitable motivation. As AI task capabilities surpass human performance in some domains, organizations naturally grant these systems greater autonomy and access privileges—mirroring how we treat valuable human employees. However, current AI systems remain fundamentally gullible, lacking robust skepticism when faced with indirect prompt injections and social engineering techniques. This talk will analyze how these three factors interact to create novel security challenges.
This is a technical presentation connecting concrete examples of generative AI system attacks to the ramifications viewed through the lense of agents as insider threats. While the audience doesn't need to have deep understanding of LLMs, the presentation will cover some basic aspects of how LLMs work and why that translates to gullibility, and give examples of agentic systems with dangerous agency.
Jason is Director of Adversarial Research at HiddenLayer, where he explores how the latest AI security research intersects with practical application. Jason was amongst the earliest researchers to recognize the need for AI security, founding the Secure Intelligence Team in Intel Labs in 2016 to research AI security and privacy threats and defenses. For 20+ years Jason has covered such diverse security topics as CPU microcode, authentication and biometrics, trusted execution environments, wearable technology, and network protocols, resulting in over 40 issued patents and several high profile research papers in adversarial machine learning and federated learning. When he’s not working Jason is either lost in the Pacific Northwest camping and hiking with his family; or he is lost in a technical project involving 3D printing, microcontrollers, or designing holiday lighting displays synchronized to music.