Keynote | Threat Modeling Agentic AI Systems: Proactive Strategies for Security and Resilience

SANS AI Cybersecurity Summit 2025 Keynote Threat Modeling Agentic AI Systems: Proactive Strategies for Security and Resilience Helen Oakley, Director of Software Supply Chains Security & Secure Development, SAP Agentic AI systems, which combine generative AI capabilities with autonomous decision-making, interact dynamically with their environment. These advanced systems bring new opportunities but also pose significant security challenges. Unlike traditional software, agentic AI operates in dynamic environments where evolving goals, actions, and external inputs can create unique threats. This session will focus on how to effectively threat model these systems, using architectural examples to illustrate their complexity and potential risks. Attendees will learn to identify critical security concerns, such as goal misalignment, unintended behaviors, and vulnerabilities in AI workflows. The session will also provide actionable strategies for integrating threat modeling into the design and deployment of agentic AI to ensure safety and reliability. View upcoming Summits: http://www.sans.org/u/DuS