Anomaly Detection and Functional Testing for Automotive CAN Communication

Integrated vehicle dynamics control systems require real-time communication among their components to improve performance and process efficiency. This communication relies on the use of sensor data, hardware interfaces, transmission protocols, and control strategies, which all have an impact on the system's reliability. However, as the number of functionalized electronic control units (ECUs) and wiring systems increases, advanced control systems encounter complex functional and cybersecurity issues. To mitigate this complexity, the automotive industry widely employs the Controller Area Network (CAN) communication bus. Nevertheless, the inherent vulnerabilities of CAN and the rich interfaces with external environments increase the systems' susceptibility to soft errors caused by uncertainty factors such as process changes. Therefore, detecting abnormalities in automotive CAN communication is crucial.This paper introduces a machine learning (ML)-based anomaly detection framework to identify anomalies through CAN messages, extracting key features and employing ML models for predictive analysis. It also uses Triple Modular Redundancy (TMR) for trusted ML computation in anomaly detection. The study provides a comparative analysis of various ML algorithms, highlighting the effectiveness of Deep Neural Networks in identifying anomalies within both synthetic and real Hyundai CAN data for a wheel speed control system, showcasing the framework's capability to enhance system reliability and security.