Abstract
Cyber resilience needs two things it still largely lacks: metrics that quantify how much adversary effort a system actually absorbs, and defenses that can act at machine speed without a human in the loop. This keynote traces both through a decade of work on critical infrastructure. On measurement, I will cover attack-graph-based ranking of vulnerabilities, exploits, and privileges for countermeasure prioritization, automated learning of adversary tradecraft from malicious campaigns, and resilience metrics developed for energy delivery, offshore wind, and port systems. On autonomy, I will cover zero-trust defense against generative-AI-driven attacks in the power grid, trust-by-learning for 6G, neuro-symbolic explainable AI twins, and agentic AI for real-time attack detection in 5G O-RAN along with the assurance problems autonomy creates. I will close with results from the STRIVEN spectrum testbed, where these ideas were validated against live radar, and an agenda for the community.
Sachin Shetty is a Professor in the Department of Electrical and Computer Engineering at Old Dominion University and Executive Director of the Center for Secure and Intelligent Critical Systems. He received his Ph.D. in Modeling and Simulation from Old Dominion University and was named a University Eminent Scholar in 2026. His research sits at the intersection of computer networking, network security, and machine learning, with a focus on cyber resilience and risk assessment for critical infrastructure, AI assurance, and 5G/6G and spectrum security. He has published over 300 peer-reviewed articles and five edited books, and has led more than $22 million in research funded by NSF, AFRL, ONR, DHS, DOE, and industry. He is a Senior Member of the IEEE.
Organizers