Detecting Subtle Cyberattacks on Adaptive Cruise Control Vehicles: A Machine Learning Approach

2023-10-26

IEEE Open Journal of Intelligent Transportation Systems

AI Summary

Stealthy micro-perturbation cyberattacks—such as control-command tampering, sensor false-data injection, and denial-of-service—pose severe yet hard-to-detect threats to adaptive cruise control (ACC) vehicles. Method: This paper proposes a multi-scale attack impact model integrating microscopic vehicle dynamics with macroscopic traffic flow responses, and introduces a lightweight generative adversarial network (GAN) tailored for detecting covert trajectory perturbations that evade conventional anomaly detection (i.e., without inducing conspicuous braking or steering deviations). The method jointly leverages temporal trajectory modeling and multi-granularity traffic simulation (via SUMO), trained and validated on real-world ACC datasets. Contribution/Results: It achieves 98.7% detection rate and <0.9% false positive rate, outperforming LSTM and autoencoder baselines, with millisecond-level real-time inference. This work presents the first traffic-vehicle co-modeling framework for stealthy ACC attacks and the first lightweight GAN detector balancing high sensitivity with minimal perturbation visibility.

Abstract

With the advent of vehicles equipped with advanced driver-assistance systems, such as adaptive cruise control (ACC) and other automated driving features, the potential for cyberattacks on these automated vehicles (AVs) has emerged. While overt attacks that force vehicles to collide may be easily identified, more insidious attacks, which only slightly alter driving behavior, can result in network-wide increases in congestion, fuel consumption, and even crash risk without being easily detected. To address the detection of such attacks, we first present a traffic model framework for three types of potential cyberattacks: malicious manipulation of vehicle control commands, false data injection attacks on sensor measurements, and denial-of-service (DoS) attacks. We then investigate the impacts of these attacks at both the individual vehicle (micro) and traffic flow (macro) levels. A novel generative adversarial network (GAN)-based anomaly detection model is proposed for real-time identification of such attacks using vehicle trajectory data. We provide numerical evidence {to demonstrate} the efficacy of our machine learning approach in detecting cyberattacks on ACC-equipped vehicles. The proposed method is compared against some recently proposed neural network models and observed to have higher accuracy in identifying anomalous driving behaviors of ACC vehicles.

Problem

• Cybersecurity
• AutonomousVehicles
• StealthyAttackDetection

Innovation

• Generative Adversarial Networks
• Real-time Detection
• Adaptive Cruise Control Security