Runtime Stealthy Perception Attacks against DNN-based Adaptive Cruise Control Systems

TL;DR

This paper demonstrates that deep neural network-based adaptive cruise control systems can be vulnerable to stealthy perception attacks that inject perturbations into camera data, significantly increasing collision risks.

Contribution

It introduces a context-aware, optimization-based method for generating adaptive, stealthy image perturbations to attack ACC systems at runtime, highlighting security vulnerabilities.

Findings

Attack success rate increased by 142.9 times compared to baselines.

82.6% higher evasion rate achieved under real-world conditions.

Attacks remain stealthy and effective despite environmental changes.

Abstract

Adaptive Cruise Control (ACC) is a widely used driver assistance technology for maintaining the desired speed and safe distance to the leading vehicle. This paper evaluates the security of the deep neural network (DNN) based ACC systems under runtime stealthy perception attacks that strategically inject perturbations into camera data to cause forward collisions. We present a context-aware strategy for the selection of the most critical times for triggering the attacks and a novel optimization-based method for the adaptive generation of image perturbations at runtime. We evaluate the effectiveness of the proposed attack using an actual vehicle, a publicly available driving dataset, and a realistic simulation platform with the control software from a production ACC system, a physical-world driving simulator, and interventions by the human driver and safety features such as Advanced Emergency Braking System (AEBS). Experimental results show that the proposed attack achieves 142.9 times higher success rate in causing hazards and 82.6% higher evasion rate than baselines, while being stealthy and robust to real-world factors and dynamic changes in the environment. This study highlights the role of human drivers and basic safety mechanisms in preventing attacks.