Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917856469319680 |
|---|---|
| author | Fan, Junchao Lei, Xuyang Chang, Xiaolin Mišić, Jelena Mišić, Vojislav B. |
| author_facet | Fan, Junchao Lei, Xuyang Chang, Xiaolin Mišić, Jelena Mišić, Vojislav B. |
| contents | Despite significant advancements in deep reinforcement learning (DRL)-based autonomous driving policies, these policies still exhibit vulnerability to adversarial attacks. This vulnerability poses a formidable challenge to the practical deployment of these policies in autonomous driving. Designing effective adversarial attacks is an indispensable prerequisite for enhancing the robustness of these policies. In view of this, we present a novel stealthy and efficient adversarial attack method for DRL-based autonomous driving policies. Specifically, we introduce a DRL-based adversary designed to trigger safety violations (e.g., collisions) by injecting adversarial samples at critical moments. We model the attack as a mixed-integer optimization problem and formulate it as a Markov decision process. Then, we train the adversary to learn the optimal policy for attacking at critical moments without domain knowledge. Furthermore, we introduce attack-related information and a trajectory clipping method to enhance the learning capability of the adversary. Finally, we validate our method in an unprotected left-turn scenario across different traffic densities. The experimental results show that our method achieves more than 90% collision rate within three attacks in most cases. Furthermore, our method achieves more than 130% improvement in attack efficiency compared to the unlimited attack method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03051 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies Fan, Junchao Lei, Xuyang Chang, Xiaolin Mišić, Jelena Mišić, Vojislav B. Machine Learning Artificial Intelligence Despite significant advancements in deep reinforcement learning (DRL)-based autonomous driving policies, these policies still exhibit vulnerability to adversarial attacks. This vulnerability poses a formidable challenge to the practical deployment of these policies in autonomous driving. Designing effective adversarial attacks is an indispensable prerequisite for enhancing the robustness of these policies. In view of this, we present a novel stealthy and efficient adversarial attack method for DRL-based autonomous driving policies. Specifically, we introduce a DRL-based adversary designed to trigger safety violations (e.g., collisions) by injecting adversarial samples at critical moments. We model the attack as a mixed-integer optimization problem and formulate it as a Markov decision process. Then, we train the adversary to learn the optimal policy for attacking at critical moments without domain knowledge. Furthermore, we introduce attack-related information and a trajectory clipping method to enhance the learning capability of the adversary. Finally, we validate our method in an unprotected left-turn scenario across different traffic densities. The experimental results show that our method achieves more than 90% collision rate within three attacks in most cases. Furthermore, our method achieves more than 130% improvement in attack efficiency compared to the unlimited attack method. |
| title | Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.03051 |