Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies
Authors:
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 31 references indexed in Scilit:
- Deep learning adversarial attacks and defenses in autonomous vehicles: a systematic literature review from a safety perspectiveArtificial Intelligence Review, 2024
- Recent advances in reinforcement learning-based autonomous driving behavior planning: A surveyTransportation Research Part C: Emerging Technologies, 2024
- Trustworthy autonomous driving via defense-aware robust reinforcement learning against worst-case observational perturbationsTransportation Research Part C: Emerging Technologies, 2024
- Deep Reinforcement Learning Based Decision-Making Strategy of Autonomous Vehicle in Highway Uncertain Driving EnvironmentsAutomotive Innovation, 2023
- On-Ramp Merging for Highway Autonomous Driving: An Application of a New Safety Indicator in Deep Reinforcement LearningAutomotive Innovation, 2023
- ATS-O2A: A state-based adversarial attack strategy on deep reinforcement learningComputers & Security, 2023
- Learning naturalistic driving environment with statistical realismNature Communications, 2023
- Predictive trajectory planning for autonomous vehicles at intersections using reinforcement learningTransportation Research Part C: Emerging Technologies, 2023
- Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies2022
- Trustworthy safety improvement for autonomous driving using reinforcement learningTransportation Research Part C: Emerging Technologies, 2022