Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning

• URL: http://arxiv.org/abs/2605.14587v1
• Date: Thu, 14 May 2026 08:58:24 GMT
• Title: Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning
• Abstract summary: We study 14,664 cases integrating representative interventions and attack scenarios.<n>We find that only one intervention (i.e., SAM) exacerbates backdoor threats, while other interventions mitigate them.<n>We derive two novel insights: (1) a conceptual framework for robust backdoor injection that interplays the mechanistic between interventions and backdoors in DRL, and (2) abnormal loss landscape sharpness as a key indicator for DRL backdoor detection.
• Score: 35.320708072497105
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Extensive research has highlighted the severe threats posed by backdoor attacks to deep reinforcement learning (DRL). However, prior studies primarily focus on vanilla scenarios, while plasticity interventions have emerged as indispensable built-in components of modern DRL agents. Despite their effectiveness in mitigating plasticity loss, the impact of these interventions on DRL backdoor vulnerabilities remains underexplored, and this lack of systematic investigation poses risks in practical DRL deployments. To bridge this gap, we empirically study 14,664 cases integrating representative interventions and attack scenarios. We find that only one intervention (i.e., SAM) exacerbates backdoor threats, while other interventions mitigate them. Pathological analysis identifies that the exacerbation is attributed to backdoor gradient amplification, while the mitigation stems from activation pathway disruption and representation space compression. From these findings, we derive two novel insights: (1) a conceptual framework SCC for robust backdoor injection that deconstructs the mechanistic interplay between interventions and backdoors in DRL, and (2) abnormal loss landscape sharpness as a key indicator for DRL backdoor detection.

Related papers

• Backdoor Unlearning by Linear Task Decomposition [69.91984435094157]
  Foundation models are highly susceptible to adversarial perturbations and targeted backdoor attacks.<n>Existing backdoor removal approaches rely on costly fine-tuning to override the harmful behavior.<n>This raises the question of whether backdoors can be removed without compromising the general capabilities of the models.
  arXiv  Detail & Related papers  (2025-10-16T16:18:07Z)
• Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning [2.1896295740048894]
  We introduce the first paradigm of revocable backdoor attacks, where the backdoor can be proactively and thoroughly removed after the attack objective is achieved.<n>This work opens a new direction for backdoor attack research and presents new challenges for the security of machine learning systems.
  arXiv  Detail & Related papers  (2025-10-15T09:09:43Z)
• 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)
• Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space [0.24578723416255752]
  This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies. It proposes a novel method for their detection at runtime.
  arXiv  Detail & Related papers  (2024-07-21T13:48:23Z)
• Variable-Agnostic Causal Exploration for Reinforcement Learning [56.52768265734155]
  We introduce a novel framework, Variable-Agnostic Causal Exploration for Reinforcement Learning (VACERL) Our approach automatically identifies crucial observation-action steps associated with key variables using attention mechanisms. It constructs the causal graph connecting these steps, which guides the agent towards observation-action pairs with greater causal influence on task completion.
  arXiv  Detail & Related papers  (2024-07-17T09:45:27Z)
• On the Difficulty of Defending Contrastive Learning against Backdoor Attacks [58.824074124014224]
  We show how contrastive backdoor attacks operate through distinctive mechanisms. Our findings highlight the need for defenses tailored to the specificities of contrastive backdoor attacks.
  arXiv  Detail & Related papers  (2023-12-14T15:54:52Z)
• BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning [85.2564206440109]
  This paper reveals the threats in this practical scenario that backdoor attacks can remain effective even after defenses. We introduce the emphtoolns attack, which is resistant to backdoor detection and model fine-tuning defenses.
  arXiv  Detail & Related papers  (2023-11-20T02:21:49Z)
• Demystifying Poisoning Backdoor Attacks from a Statistical Perspective [35.30533879618651]
  Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious consequences. This paper evaluates the effectiveness of any backdoor attack incorporating a constant trigger. Our derived understanding applies to both discriminative and generative models.
  arXiv  Detail & Related papers  (2023-10-16T19:35:01Z)
• Backdoor Defense via Suppressing Model Shortcuts [91.30995749139012]
  In this paper, we explore the backdoor mechanism from the angle of the model structure. We demonstrate that the attack success rate (ASR) decreases significantly when reducing the outputs of some key skip connections.
  arXiv  Detail & Related papers  (2022-11-02T15:39:19Z)
• A Temporal-Pattern Backdoor Attack to Deep Reinforcement Learning [10.162123678104917]
  We propose a novel temporal-pattern backdoor attack to DRL. We validate our proposed backdoor attack to a typical job scheduling task in cloud computing. Our backdoor's average clean data accuracy and attack success rate can reach 97.8% and 97.5%, respectively.
  arXiv  Detail & Related papers  (2022-05-05T12:03:09Z)

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.