# Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems

Source: [Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems](<https://www.sota2.com/research/paper/68fa78b51e209131cea79e81>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:44:13.662Z

Authors: Cheng Chen, Yuhong Wang, Nafis S Munir, Xiangwei Zhou, Xugui Zhou

Published: 2025-05-14T02:05:34.000Z

## Abstract

Autonomous driving systems (ADS) increasingly rely on deep learning-based perception models, which remain vulnerable to adversarial attacks. In this paper, we revisit adversarial attacks and defense methods, focusing on road sign recognition and lead object detection and prediction (e.g., relative distance). Using a Level-2 production ADS, OpenPilot by Comma$.$ai, and the widely adopted YOLO model, we systematically examine the impact of adversarial perturbations and assess defense techniques, including adversarial training, image processing, contrastive learning, and diffusion models. Our experiments highlight both the strengths and limitations of these methods in mitigating complex attacks. Through targeted evaluations of model robustness, we aim to provide deeper insights into the vulnerabilities of ADS perception systems and contribute guidance for developing more resilient defense strategies.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2505.11532>)

[PDF](<https://arxiv.org/pdf/2505.11532.pdf>)
