Detecting Masquerade Attacks in Controller Area Networks Using Graph Machine Learning
This addresses a critical cybersecurity issue for modern vehicles, where masquerade attacks can cause severe safety risks like unintended acceleration, and it is incremental by enhancing existing graph-based methods with time series features.
The paper tackled the problem of detecting masquerade attacks in controller area networks (CANs) for vehicles by introducing a graph machine learning framework that integrates shallow graph embeddings with time series features, resulting in statistically significant improvements in detection rates compared to a baseline using only graph-based features.
Modern vehicles rely on a myriad of electronic control units (ECUs) interconnected via controller area networks (CANs) for critical operations. Despite their ubiquitous use and reliability, CANs are susceptible to sophisticated cyberattacks, particularly masquerade attacks, which inject false data that mimic legitimate messages at the expected frequency. These attacks pose severe risks such as unintended acceleration, brake deactivation, and rogue steering. Traditional intrusion detection systems (IDS) often struggle to detect these subtle intrusions due to their seamless integration into normal traffic. This paper introduces a novel framework for detecting masquerade attacks in the CAN bus using graph machine learning (ML). We hypothesize that the integration of shallow graph embeddings with time series features derived from CAN frames enhances the detection of masquerade attacks. We show that by representing CAN bus frames as message sequence graphs (MSGs) and enriching each node with contextual statistical attributes from time series, we can enhance detection capabilities across various attack patterns compared to using graph-based features only. Our method ensures a comprehensive and dynamic analysis of CAN frame interactions, improving robustness and efficiency. Extensive experiments on the ROAD dataset validate the effectiveness of our approach, demonstrating statistically significant improvements in the detection rates of masquerade attacks compared to a baseline that uses graph-based features only as confirmed by Mann-Whitney U and Kolmogorov-Smirnov tests p < 0.05.