Intrusion Detection Methods in Communication-Based Train Control Systems Based on Relative Entropy and Trust Evaluation

The existing intrusion detection system (IDS) does not consider the security and credibility problem of its own. An IDS captured by cyber attackers may generate lots of malicious alarms which will seriously impact the operation of communication-based train control (CBTC) systems. In this paper, we analyze the information exchange characteristics of CBTC systems and propose an IDS based on distributed trusted infrastructure. The method of relative entropy is adopted for intrusion detection. In addition, a trust evaluation model is developed based on the fuzzy theory to evaluate the credibility of IDSs. Simulation results show that the proposed IDS can effectively detect the malicious alarms and eliminate their effects on the operation of CBTC systems. The detection rate can reach over 95%.