Security and Interpretability in Automotive Systems

Abstract

Controller area network (CAN) is the most commonly found bus protocol in automotive systems. The two-wire bus protocol helps accomplish sophisticated vehicle services in real-time through complex interactions between hardware components. However, the lack of any sender authentication mechanism in place makes CAN susceptible to security vulnerabilities and threats. To address the insecure nature of the system, this thesis demonstrates a sender authentication technique that uses power consumption measurements of the electronic control units (ECUs) and a classification model to determine the transmitting states of the ECUs. The method's evaluation in real-world settings shows that the technique applies in a broad range of operating conditions and achieves good accuracy.

A key challenge of machine learning-based security controls is the potential of false positives. A false-positive alert may induce panic in operators, lead to incorrect reactions, and in the long run cause alarm fatigue. For reliable decision-making in such a circumstance, knowing the cause for unusual model behavior is essential. But, the black-box nature of these models makes them uninterpretable. Therefore, another contribution of this thesis explores explanation techniques for inputs of type image and time series that (1) assign weights to individual inputs based on their sensitivity toward the target class, (2) and quantify the variations in the explanation by reconstructing the sensitive regions of the inputs using a generative model.

In summary, this thesis presents methods for addressing the security and interpretability in automotive systems, which can also be applied in other settings where safe, transparent, and reliable decision-making is crucial.