TENET: Temporal CNN with Attention for Anomaly Detection in Automotive Cyber-Physical Systems
This addresses security vulnerabilities in modern vehicles, offering a more efficient and accurate detection method, though it appears incremental as it builds on existing temporal CNN and attention approaches.
The paper tackles anomaly detection for cyber-attacks in automotive cyber-physical systems by proposing TENET, a framework using temporal CNNs with attention, which achieved improvements such as a 32.70% reduction in False Negative Rate and 94.62% fewer parameters compared to prior work.
Modern vehicles have multiple electronic control units (ECUs) that are connected together as part of a complex distributed cyber-physical system (CPS). The ever-increasing communication between ECUs and external electronic systems has made these vehicles particularly susceptible to a variety of cyber-attacks. In this work, we present a novel anomaly detection framework called TENET to detect anomalies induced by cyber-attacks on vehicles. TENET uses temporal convolutional neural networks with an integrated attention mechanism to detect anomalous attack patterns. TENET is able to achieve an improvement of 32.70% in False Negative Rate, 19.14% in the Mathews Correlation Coefficient, and 17.25% in the ROC-AUC metric, with 94.62% fewer model parameters, 86.95% decrease in memory footprint, and 48.14% lower inference time when compared to the best performing prior work on automotive anomaly detection.