Safeguarding Smart Vehicles: GNN-Powered Real- Time IDS for CAN Networks

With the increasing integration of Controller Area Network (CAN) in modern vehicles, securing the communication network from malicious attacks is imperative. A novel Graph Neural Network (GNN)-based Intrusion Detection System (IDS) is proposed for real-time detection of several attacks, such as Denial of Service (DOS), fuzzy, and spoofing attacks. Our proposed model represents the CAN network as a graph, where nodes correspond to message arbitration ID and edges denote the communication sequence. Using Graph Attention Networks (GAT), our model captures the intricate relationships and dependencies between Electronic Circuit Units (ECUs), in real-time, enhancing its ability to discern normal behavior from malicious activity. The key to our system's success is its emphasis on achieving real-time capabilities. The GAT architecture optimizes computational efficiency for swift analysis of CAN traffic without compromising detection accuracy. Our system minimizes model complexity for enhanced deployability in resource-constrained vehicular environments. Comprehensive experiments on a diverse dataset showcase its ability to swiftly and accurately detect a range of attacks in real-time, with an overall accuracy of 99.75% for DOS attacks, 99.50% for fuzzy attacks, and 100% for spoofing attacks. Moreover, attack detection time is calculated to be 6.76 ms for DOS, 6.79 ms for fuzzy, and 6.69 ms for spoofing. These results made the model meet real-time detection constraints.