Predicting Malicious Intention in CPS under Cyber-Attack

Modern autonomous cyber-physical systems (CPS) have been demonstrated to be vulnerable to cyber-attacks like sensor spoofing in which an attacker compromises sensor readings while remaining stealthy to hijack the system toward undesired states. The majority of security techniques developed today are, however, reactive and concerned with detection and interdiction of attacks without considering predicting the intention of the attack. To deal with such problem, we propose a Reachability-based approach and a Bayesian Inverse Reinforcement Learning technique that leverages the history of sensor data and control inputs to assess the risk and predict the goal of sensor spoofing attacks, determine which sensors are compromised, and recover the system.