Sharpening the Spear: Adaptive Expert-Guided Adversarial Attack Against DRL-based Autonomous Driving Policies

• URL: http://arxiv.org/abs/2506.18304v1
• Date: Mon, 23 Jun 2025 05:42:49 GMT
• Title: Sharpening the Spear: Adaptive Expert-Guided Adversarial Attack Against DRL-based Autonomous Driving Policies
• Authors: Junchao Fan, Xuyang Lei, Xiaolin Chang,
• Abstract summary: Deep reinforcement learning (DRL) has emerged as a promising paradigm for autonomous driving.<n>DRL-based policies remain highly vulnerable to adversarial attacks, posing serious safety risks in real-world deployments.<n>We propose an adaptive expert-guided adversarial attack method that enhances both the stability and efficiency of attack policy training.
• Score: 3.5120264792560993
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep reinforcement learning (DRL) has emerged as a promising paradigm for autonomous driving. However, despite their advanced capabilities, DRL-based policies remain highly vulnerable to adversarial attacks, posing serious safety risks in real-world deployments. Investigating such attacks is crucial for revealing policy vulnerabilities and guiding the development of more robust autonomous systems. While prior attack methods have made notable progress, they still face several challenges: 1) they often rely on high-frequency attacks, yet critical attack opportunities are typically context-dependent and temporally sparse, resulting in inefficient attack patterns; 2) restricting attack frequency can improve efficiency but often results in unstable training due to the adversary's limited exploration. To address these challenges, we propose an adaptive expert-guided adversarial attack method that enhances both the stability and efficiency of attack policy training. Our method first derives an expert policy from successful attack demonstrations using imitation learning, strengthened by an ensemble Mixture-of-Experts architecture for robust generalization across scenarios. This expert policy then guides a DRL-based adversary through a KL-divergence regularization term. Due to the diversity of scenarios, expert policies may be imperfect. To address this, we further introduce a performance-aware annealing strategy that gradually reduces reliance on the expert as the adversary improves. Extensive experiments demonstrate that our method achieves outperforms existing approaches in terms of collision rate, attack efficiency, and training stability, especially in cases where the expert policy is sub-optimal.

Related papers

• Reinforcement Learning for Decision-Level Interception Prioritization in Drone Swarm Defense [56.47577824219207]
  We present a case study demonstrating the practical advantages of reinforcement learning in addressing this challenge.<n>We introduce a high-fidelity simulation environment that captures realistic operational constraints.<n>Agent learns to coordinate multiple effectors for optimal interception prioritization.<n>We evaluate the learned policy against a handcrafted rule-based baseline across hundreds of simulated attack scenarios.
  arXiv  Detail & Related papers  (2025-08-01T13:55:39Z)
• Policy Disruption in Reinforcement Learning:Adversarial Attack with Large Language Models and Critical State Identification [8.292056374554162]
  Reinforcement learning (RL) has achieved remarkable success in fields like robotics and autonomous driving.<n>Existing approaches often rely on modifying the environment or policy, limiting their practicality.<n>This paper proposes an adversarial attack method in which existing agents in the environment guide the target policy to output suboptimal actions without altering the environment.
  arXiv  Detail & Related papers  (2025-07-24T05:52:06Z)
• Target Defense with Multiple Defenders and an Agile Attacker via Residual Policy Learning [0.918715978278858]
  This letter focuses on a particularly challenging scenario in which the attacker is more agile than the defenders.<n>We propose a novel residual policy framework that integrates deep reinforcement learning with the force-based Boids model.<n>In this framework, the Boids model serves as a baseline policy, while DRL learns a residual policy to refine and optimize the defenders' actions.
  arXiv  Detail & Related papers  (2025-02-25T16:05:33Z)
• 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)
• Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses [19.918548094276005]
  offline reinforcement learning (RL) addresses the challenge of expensive and high-risk data exploration inherent in RL by pre-training policies on vast amounts of offline data. This paper proposes a framework to enhance the robustness of offline RL models by leveraging advanced adversarial attacks and defenses.
  arXiv  Detail & Related papers  (2024-05-18T07:23:44Z)
• 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)
• Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey [8.1138182541639]
  Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments.<n>It remains susceptible to minor condition variations, raising concerns about its reliability in real-world applications.<n>A way to improve robustness of DRL to unknown changes in the environmental conditions and possible perturbations is through Adversarial Training.
  arXiv  Detail & Related papers  (2024-03-01T10:16:46Z)
• Embodied Laser Attack:Leveraging Scene Priors to Achieve Agent-based Robust Non-contact Attacks [13.726534285661717]
  This paper introduces the Embodied Laser Attack (ELA), a novel framework that dynamically tailors non-contact laser attacks. For the perception module, ELA has innovatively developed a local perspective transformation network, based on the intrinsic prior knowledge of traffic scenes. For the decision and control module, ELA trains an attack agent with data-driven reinforcement learning instead of adopting time-consuming algorithms.
  arXiv  Detail & Related papers  (2023-12-15T06:16:17Z)
• Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning [64.11013095004786]
  We propose a dual-agent safe reinforcement learning strategy consisting of a baseline and a safe agent. Such a decoupled framework enables high flexibility, data efficiency and risk-awareness for RL-based control. The proposed method outperforms the state-of-the-art safe RL algorithms on difficult robot locomotion and manipulation tasks.
  arXiv  Detail & Related papers  (2022-12-14T03:11:25Z)
• Attacking and Defending Deep Reinforcement Learning Policies [3.6985039575807246]
  We study robustness of DRL policies to adversarial attacks from the perspective of robust optimization. We propose a greedy attack algorithm, which tries to minimize the expected return of the policy without interacting with the environment, and a defense algorithm, which performs adversarial training in a max-min form.
  arXiv  Detail & Related papers  (2022-05-16T12:47:54Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)
• Robust Reinforcement Learning on State Observations with Learned Optimal Adversary [86.0846119254031]
  We study the robustness of reinforcement learning with adversarially perturbed state observations. With a fixed agent policy, we demonstrate that an optimal adversary to perturb state observations can be found. For DRL settings, this leads to a novel empirical adversarial attack to RL agents via a learned adversary that is much stronger than previous ones.
  arXiv  Detail & Related papers  (2021-01-21T05:38:52Z)
• Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses [59.58128343334556]
  We introduce a relaxation term to the standard loss, that finds more suitable gradient-directions, increases attack efficacy and leads to more efficient adversarial training. We propose Guided Adversarial Margin Attack (GAMA), which utilizes function mapping of the clean image to guide the generation of adversaries. We also propose Guided Adversarial Training (GAT), which achieves state-of-the-art performance amongst single-step defenses.
  arXiv  Detail & Related papers  (2020-11-30T16:39:39Z)
• Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agents [23.580682320064714]
  This work investigates targeted attacks in the action-space domain, also commonly known as actuation attacks in CPS literature. We show that a query-based black-box attack model that generates optimal perturbations with respect to an adversarial goal can be formulated as another reinforcement learning problem. Experimental results showed that adversarial policies that only observe the nominal policy's output generate stronger attacks than adversarial policies that observe the nominal policy's input and output.
  arXiv  Detail & Related papers  (2020-11-13T20:25:48Z)
• Conservative Safety Critics for Exploration [120.73241848565449]
  We study the problem of safe exploration in reinforcement learning (RL) We learn a conservative safety estimate of environment states through a critic. We show that the proposed approach can achieve competitive task performance while incurring significantly lower catastrophic failure rates.
  arXiv  Detail & Related papers  (2020-10-27T17:54:25Z)

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.