Cyber-Physical Collaborative Defense Framework Using Artificial Intelligence for Cross-Domain Attacks in Power Systems

Power infrastructure has evolved into a cyber-physical system (CPS) characterized by high levels of informatization, automation, and intelligence. While this integration of the information and physical domains significantly improves the efficiency and performance of power supply, it also introduces novel cyber-security threats. Cross-domain attacks, which originate in the information domain and directly affect the physical domain, can cause systemic paralysis of power infrastructure and potentially trigger large-scale blackouts. Current defense systems that focus solely on either the information or physical domain are insufficient to counter these cross-domain threats effectively. This paper presents a cyber-physical collaborative defense framework, enhanced by artificial intelligence, to address these challenges. The framework develops defense strategies from three perspectives—perception, identification, and disruption—targeting different stages of cross-domain attack propagation. Case studies demonstrate that the proposed AI-driven cyber-physical collaborative defense framework can effectively ensure the safe and stable operation of power systems.