Sensor and Decision Fusion-Based Intrusion Detection and Mitigation Approach for Connected Autonomous Vehicles

The safety of connected and autonomous vehicle (CAV) depends on the security of in-vehicle communication. The controller area network (CAN) bus holds a crucial position in ensuring in-vehicle security. Injecting attacks (e.g., increasing the speed) by hackers can affect drivers. This article proposes a fusion intrusion detection and resilient approach to maintain system performance against intrusion. The proposed system consists of two parts: sensor validation and sensor value estimation. In the sensor validation step, a new fusion approach uses three feature ranking approaches, autoencoder, and estimator-based detectors. Finally, Yager’s rules are used to handle conflict between classifiers and enrich intrusion detection accuracy. Afterward, in the second part, if any intrusion is detected, the estimated values of that sensor which is under intrusion will be replaced based on estimated values by long short-term memory-based deep regressor (LSTMDR) to avoid any performance disruption of the system. The main contribution of this study is that the proposed fusion approach uses the inherent redundancy among heterogeneous sensors to create a resilient system against compromised sensors. Using Yager’s rule and the ordered weighted average for information fusion significantly increases the reliability of intrusion detection systems and improves their detection rates. It also improves the performance of soft sensors and enhances the effectiveness of the mitigation phase. To evaluate the proposed approach, a real-world dataset entitled AEGIS—advanced big data value chain for public safety and personal security—is used. Test results indicate that the proposed fusion method is robust and reaches more accurate results compared with other detectors in three different considered attacks including replay, denial of service, and false data injection.