TENET: Temporal CNN with Attention for Anomaly Detection in Automotive Cyber-Physical Systems

TL;DR

TENET is a novel anomaly detection framework utilizing temporal CNNs with attention mechanisms to identify cyber-attacks in automotive cyber-physical systems, significantly improving detection metrics and efficiency over prior methods.

Contribution

The paper introduces TENET, a new anomaly detection model combining temporal CNNs and attention, with substantial performance and efficiency improvements for automotive cyber-physical security.

Findings

32.70% reduction in False Negative Rate

94.62% fewer model parameters

48.14% lower inference time

Abstract

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.