DESC-IDS: Towards an efficient real-time automotive intrusion detection system based on deep evolving stream clustering

Pengzhou Cheng, Mu Han, Gongshen Liu

Abstract: Highlights•DESC-IDS is proposed by integrating the SRCAE module and stream clustering layer.•SRCAE can extract valuable features and reconstruct unknown attacks.•The stream clustering layer detects any abnormal by the contour of normal messages.•The performance of DESC-IDS is demonstrated in extensive evaluation experiments.