Impact Analysis of Inference Time Attack of Perception Sensors on Autonomous Vehicles

TL;DR

This paper investigates how inference time attacks on perception sensors can compromise the safety of autonomous vehicles, highlighting security vulnerabilities beyond perception correctness through simulation-based impact analysis.

Contribution

It introduces an impact analysis framework for inference time attacks on AV perception modules, demonstrating potential safety threats in simulation environments.

Findings

Inference time attacks can threaten vehicle safety

Simulation shows impact on ego vehicle and traffic participants

Highlights need for security measures in perception systems

Abstract

As a safety-critical cyber-physical system, cybersecurity and related safety issues for Autonomous Vehicles (AVs) have been important research topics for a while. Among all the modules on AVs, perception is one of the most accessible attack surfaces, as drivers and AVs have no control over the outside environment. Most current work targeting perception security for AVs focuses on perception correctness. In this work, we propose an impact analysis based on inference time attacks for autonomous vehicles. We demonstrate in a simulation system that such inference time attacks can also threaten the safety of both the ego vehicle and other traffic participants.