An Intrusion Detection Method Based on Self-Generated Coding Technology for Stealthy False Data Injection Attacks in Train-Ground Communication Systems

Abstract

This paper investigates the problem of intrusion detection of stealthy false data injection (FDI) attacks in train-ground communication systems. An intrusion detection method is proposed based on the self-generated coding technology. Different from the existing pseudo-random coding generators-based detection methods, the proposed method designs a self-generated multiplicative coding scheme by employing the authentication mechanism, where the coding sequences to encrypt and decrypt the original measurement data of trains are dynamically updated by parsing the latest timestamp online such that the attacker is not able to obtain the prior knowledge of the coding sequences, which improves the security of the data transmission in the train-ground communication network. Under stealthy FDI attacks, the proposed method increases the output residuals of the remote state estimator, which ensures that the residual-based detector continuously outputs alarm. Furthermore, in order to mitigate the impact of the attack on the system, a dead reckoning algorithm-based defence model is established to reconstruct the position information of trains compromised by the attacker. Finally, the effectiveness and superiority of the proposed method are verified through semi-physical simulation experiments.