Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909621363408896 |
|---|---|
| author | Chen, Cheng Wang, Yuhong Munir, Nafis S Zhou, Xiangwei Zhou, Xugui |
| author_facet | Chen, Cheng Wang, Yuhong Munir, Nafis S Zhou, Xiangwei Zhou, Xugui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_11532 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems Chen, Cheng Wang, Yuhong Munir, Nafis S Zhou, Xiangwei Zhou, Xugui Robotics Cryptography and Security 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. |
| title | Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems |
| topic | Robotics Cryptography and Security |
| url | https://arxiv.org/abs/2505.11532 |