Affiliation:
1. School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing 100876, China
2. Department of Computer Science and Technology, Ocean University of China, Qingdao 266100, China
Abstract
As the number and computational power of electronic computing units installed in standard automobiles continue to increase, contemporary motor vehicles face more cybersecurity threats than previous designs, while providing greater convenience and various useful features. Although vehicles are attacked at various entry points, eventually, attacks are injected into the in-vehicle controller area network (CAN) to cause vehicle anomalies. Currently, OEMs and research fields have implemented protection for the CAN bus in terms of external interfaces, internal protocols, and intrusion detection. Although the deployment of intrusion detection solutions is the most effective approach, the main challenges currently faced by automobile intrusion detection algorithms in practice involve limited computing resources, insufficient real-time responsiveness, and low recognition accuracy. In this study, we propose a novel intrusion detection method based on the message and time transfer matrix to address these difficulties, which can be applied to the vehicle Electronic Control Unit (ECU) to achieve real-time attack signal identification with high accuracy. Experiments on actual vehicles show that the proposed algorithm identified various attacks with high accuracy while consuming less computational and storage resources than previous methods. Moreover, the efficiency of the proposed algorithm is not affected by the attack injection frequency. Compared with other methods, the proposed method achieved better attack identification performance. Additionally, the message and time transfer matrix used by the algorithm can be used as a message transfer fingerprint of the CAN bus to discover anomalies.
Funder
China Postdoctoral Science Foundation
Subject
Computer Networks and Communications,Information Systems
Cited by
10 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献