AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models

• URL: http://arxiv.org/abs/2503.20804v1
• Date: Mon, 24 Mar 2025 14:59:17 GMT
• Title: AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Models
• Authors: Le Qiu, Zelai Xu, Qixin Tan, Wenhao Tang, Chao Yu, Yu Wang,
• Abstract summary: We propose a framework that uses large language models (LLMs) to automatically discover effective and diverse vulnerabilities in autonomous driving policies.<n> Experiments show that AED achieves a broader range of vulnerabilities and higher attack success rates compared with expert-designed rewards.
• Score: 7.923448458349885
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Assessing the safety of autonomous driving policy is of great importance, and reinforcement learning (RL) has emerged as a powerful method for discovering critical vulnerabilities in driving policies. However, existing RL-based approaches often struggle to identify vulnerabilities that are both effective-meaning the autonomous vehicle is genuinely responsible for the accidents-and diverse-meaning they span various failure types. To address these challenges, we propose AED, a framework that uses large language models (LLMs) to automatically discover effective and diverse vulnerabilities in autonomous driving policies. We first utilize an LLM to automatically design reward functions for RL training. Then we let the LLM consider a diverse set of accident types and train adversarial policies for different accident types in parallel. Finally, we use preference-based learning to filter ineffective accidents and enhance the effectiveness of each vulnerability. Experiments across multiple simulated traffic scenarios and tested policies show that AED uncovers a broader range of vulnerabilities and achieves higher attack success rates compared with expert-designed rewards, thereby reducing the need for manual reward engineering and improving the diversity and effectiveness of vulnerability discovery.

Related papers

• Optimal Actuator Attacks on Autonomous Vehicles Using Reinforcement Learning [11.836584342902492]
  We propose a reinforcement learning (RL)-based approach for designing optimal stealthy integrity attacks on AV actuators. We also analyze the limitations of state-of-the-art RL-based secure controllers to counter such attacks.
  arXiv  Detail & Related papers  (2025-02-11T03:01:05Z)
• TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning [61.33599727106222]
  TeLL-Drive is a hybrid framework that integrates a Teacher LLM to guide an attention-based Student DRL policy.<n>A self-attention mechanism then fuses these strategies with the DRL agent's exploration, accelerating policy convergence and boosting robustness.
  arXiv  Detail & Related papers  (2025-02-03T14:22:03Z)
• Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving [65.61999354218628]
  We take the first step toward designing black-box adversarial attacks specifically targeting vision-language models (VLMs) in autonomous driving systems. We propose Cascading Adversarial Disruption (CAD), which targets low-level reasoning breakdown by generating and injecting semantics. We present Risky Scene Induction, which addresses dynamic adaptation by leveraging a surrogate VLM to understand and construct high-level risky scenarios.
  arXiv  Detail & Related papers  (2025-01-23T11:10:02Z)
• Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving [9.39122455540358]
  Reinforcement Learning (RL) has shown excellent performance in solving decision-making and control problems of autonomous driving. Driving is a multi-attribute problem, leading to challenges in achieving multi-objective compatibility for current RL methods. We propose a Multi-objective Ensemble-Critic reinforcement learning method with Hybrid Parametrized Action for multi-objective compatible autonomous driving.
  arXiv  Detail & Related papers  (2025-01-14T13:10:13Z)
• Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models [62.12822290276912]
  Auto-RT is a reinforcement learning framework that automatically explores and optimize complex attack strategies.<n>By significantly improving exploration efficiency and automatically optimizing attack strategies, Auto-RT detects a boarder range of vulnerabilities, achieving a faster detection speed and 16.63% higher success rates compared to existing methods.
  arXiv  Detail & Related papers  (2025-01-03T14:30:14Z)
• Less is More: A Stealthy and Efficient Adversarial Attack Method for DRL-based Autonomous Driving Policies [2.9965913883475137]
  We present a stealthy and efficient adversarial attack method for DRL-based autonomous driving policies.<n>We train the adversary to learn the optimal policy for attacking at critical moments without domain knowledge.<n>Our method achieves more than 90% collision rate within three attacks in most cases.
  arXiv  Detail & Related papers  (2024-12-04T06:11:09Z)
• CIMRL: Combining IMitation and Reinforcement Learning for Safe Autonomous Driving [45.05135725542318]
  IMitation and Reinforcement Learning (CIMRL) approach enables training driving policies in simulation through leveraging imitative motion priors and safety constraints. By combining RL and imitation, we demonstrate our method achieves state-of-the-art results in closed loop simulation and real world driving benchmarks.
  arXiv  Detail & Related papers  (2024-06-13T07:31:29Z)
• Work-in-Progress: Crash Course: Can (Under Attack) Autonomous Driving Beat Human Drivers? [60.51287814584477]
  This paper evaluates the inherent risks in autonomous driving by examining the current landscape of AVs. We develop specific claims highlighting the delicate balance between the advantages of AVs and potential security challenges in real-world scenarios.
  arXiv  Detail & Related papers  (2024-05-14T09:42:21Z)
• RACER: Epistemic Risk-Sensitive RL Enables Fast Driving with Fewer Crashes [57.319845580050924]
  We propose a reinforcement learning framework that combines risk-sensitive control with an adaptive action space curriculum. We show that our algorithm is capable of learning high-speed policies for a real-world off-road driving task.
  arXiv  Detail & Related papers  (2024-05-07T23:32:36Z)
• Empowering Autonomous Driving with Large Language Models: A Safety Perspective [82.90376711290808]
  This paper explores the integration of Large Language Models (LLMs) into Autonomous Driving systems. LLMs are intelligent decision-makers in behavioral planning, augmented with a safety verifier shield for contextual safety learning. We present two key studies in a simulated environment: an adaptive LLM-conditioned Model Predictive Control (MPC) and an LLM-enabled interactive behavior planning scheme with a state machine.
  arXiv  Detail & Related papers  (2023-11-28T03:13:09Z)
• Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms [0.0]
  We propose a self-improving artificial intelligence system to enhance the safety performance of reinforcement learning (RL)-based autonomous driving (AD) agents. Our approach efficiently discovers safety failures of action decisions in RL-based adaptive cruise control (ACC) applications.
  arXiv  Detail & Related papers  (2022-10-29T11:34:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.