PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent

• URL: http://arxiv.org/abs/2606.12896v1
• Date: Thu, 11 Jun 2026 04:54:28 GMT
• Title: PolicyGuard: Towards Test-time and Step-level Adversary Defense for Reinforcement Learning Agent
• Abstract summary: We propose textttPolicyGuard, a textittest-time step-level backdoor defense for reinforcement learning.<n>PolicyGuard achieves state-of-the-art detection performance in most cases, with average AUROC of 0.856 for perturbation-based attacks and 0.859 for adversary-agent attacks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While real-world applications of reinforcement learning (RL) are becoming increasingly popular, the security of RL systems deserve more attention and exploration. In particular, recent work has revealed that RL agents are vulnerable to backdoor attacks, where a victim agent behaves normally under standard conditions but executes malicious actions when a specific trigger is activated. Existing backdoor defenses for RL either require access to the agent's internal parameters, operate only at the model or trajectory level, or are limited to specific attack types. To ensure the security of RL agents, we propose \texttt{PolicyGuard}, a \textit{test-time step-level} backdoor defense which leverages Gaussian Process (GP) posterior variance and adapts pseudo trajectories to enable uncertainty computation for individual time step. Besides, we also provide theoretical foundations to explain the efficacy of GP posterior variance. Extensive experiments across seven RL games demonstrate that PolicyGuard achieves state-of-the-art detection performance in most cases, with average AUROC of 0.856 for perturbation-based attacks and 0.859 for adversary-agent attacks.

Related papers

• StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing [80.39644823192113]
  We propose StepGuard, a step-level guard model that can audit completed agent trajectories and check tool actions before they are executed.<n>StepGuard achieves the highest average accuracy among open-weight guard models, with performance comparable to GPT-5.4.<n>When used to guard agents on AgentDojo and AgentDyn, StepGuard reduces mean attack success rate by 77.3%.
  arXiv  Detail & Related papers  (2026-08-25T16:17:27Z)
• BehaviorGuard: Online Backdoor Defense for Deep Reinforcement Learning [32.53874142863277]
  Backdoor attacks pose a serious threat to deep reinforcement learning (DRL)<n>Current defenses rely on reward anomalies to reverse-engineer triggers and model finetuning to remove backdoors.<n>We propose BehaviorGuard, an online behavior-based backdoor detection and mitigation framework for DRL.
  arXiv  Detail & Related papers  (2026-05-07T10:21:14Z)
• Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning [2.8311497176067104]
  Deep Reinforcement Learning (DRL) systems are increasingly used in safety-critical applications, yet their security remains severely underexplored.<n>This work investigates backdoor attacks, which implant hidden triggers that cause malicious actions only when specific inputs appear in the observation space.<n>We introduce two novel attacks: (1) TrojanentRL, which exploits component-level flaws to implant a persistent backdoor that survives full model retraining; and (2) InfrectroRL, a post-training backdoor attack which requires no access to training, validation, nor test data.
  arXiv  Detail & Related papers  (2025-07-07T11:15:54Z)
• Adversarial Inception Backdoor Attacks against Reinforcement Learning [16.350898218047405]
  Recent works have demonstrated the vulnerability of Deep Reinforcement Learning (DRL) algorithms against training-time, backdoor poisoning attacks.<n>We propose a new class of backdoor attacks against DRL which are the first to achieve state of the art performance under strict reward constraints.
  arXiv  Detail & Related papers  (2024-10-17T19:50:28Z)
• AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases [73.04652687616286]
  We propose AgentPoison, the first backdoor attack targeting generic and RAG-based LLM agents by poisoning their long-term memory or RAG knowledge base. Unlike conventional backdoor attacks, AgentPoison requires no additional model training or fine-tuning. On each agent, AgentPoison achieves an average attack success rate higher than 80% with minimal impact on benign performance.
  arXiv  Detail & Related papers  (2024-07-17T17:59:47Z)
• Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift [104.76588209308666]
  This paper explores backdoor attacks in LVLM instruction tuning across mismatched training and testing domains.<n>We introduce a new evaluation dimension, backdoor domain generalization, to assess attack robustness.<n>We propose a multimodal attribution backdoor attack (MABA) that injects domain-agnostic triggers into critical areas.
  arXiv  Detail & Related papers  (2024-06-27T02:31:03Z)
• BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models [57.5404308854535]
  Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. We present BEEAR, a mitigation approach leveraging the insight that backdoor triggers induce relatively uniform drifts in the model's embedding space. Our bi-level optimization method identifies universal embedding perturbations that elicit unwanted behaviors and adjusts the model parameters to reinforce safe behaviors against these perturbations.
  arXiv  Detail & Related papers  (2024-06-24T19:29:47Z)
• SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents [16.350898218047405]
  Reinforcement learning (RL) is an actively growing field that is seeing increased usage in real-world, safety-critical applications. In this work we explore a particularly stealthy form of training-time attacks against RL -- backdoor poisoning. We formulate a novel poisoning attack framework which interlinks the adversary's objectives with those of finding an optimal policy.
  arXiv  Detail & Related papers  (2024-05-30T23:31:25Z)
• SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks [53.28390057407576]
  Modern NLP models are often trained on public datasets drawn from diverse sources. Data poisoning attacks can manipulate the model's behavior in ways engineered by the attacker. Several strategies have been proposed to mitigate the risks associated with backdoor attacks.
  arXiv  Detail & Related papers  (2024-05-19T14:50:09Z)
• BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learning [37.19070609394519]
  Backdoor attacks in reinforcement learning (RL) have previously employed intense attack strategies to ensure attack success. In this work, we propose a novel approach, BadRL, which focuses on conducting highly sparse backdoor poisoning efforts during training and testing. Our algorithm, BadRL, strategically chooses state observations with high attack values to inject triggers during training and testing, thereby reducing the chances of detection.
  arXiv  Detail & Related papers  (2023-12-19T20:29:29Z)
• Robust Deep Reinforcement Learning through Adversarial Loss [74.20501663956604]
  Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent's inputs. We propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against adversarial attacks.
  arXiv  Detail & Related papers  (2020-08-05T07:49:42Z)
• Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations [88.94162416324505]
  A deep reinforcement learning (DRL) agent observes its states through observations, which may contain natural measurement errors or adversarial noises. Since the observations deviate from the true states, they can mislead the agent into making suboptimal actions. We show that naively applying existing techniques on improving robustness for classification tasks, like adversarial training, is ineffective for many RL tasks.
  arXiv  Detail & Related papers  (2020-03-19T17:59:59Z)

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.