CPS Attack Detection of Ships using Particle Filter

In this paper, a method based on particle filter (PF) is proposed to detect the attack on cyber-physical Systems (CPS) of ships. Considering that CPS usually has state delay and Markov property, this paper estimates the markov jumping parameters of the time-series amplified system by particle filter, and estimates the system state by using Kalman filter. The residual evaluation function is designed to detect whether the attack exists. The above method is verified by the real ship data, which proves that the method can be used in the actual CPS attack detection and shows a good detection effect.