Provable Privacy and Security for Autonomous Agents - Are We There Yet?

In this talk, we take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens, efforts to increase model robustness (the dominant viewpoint in the ML community) are insufficient on their own. Instead, we must complement existing efforts with techniques from the systems security domain. We will cover some example solutions that follow this viewpoint, and discuss their pros and cons. We will also identify the challenges that stand in the way of implementing these principles in agents.

Speaker: Shomesh Jha, University of Wisconsin