mlsanityData to 14 Oct 2026

Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee

arXiv 2405.15245 ↗First posted 24 May 2024cs.LG cs.AIcited by 6

On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance

Abstract (arXiv)

The safety of decentralized reinforcement learning (RL) is a challenging problem since malicious agents can share their poisoned policies with benign agents. The paper investigates a cooperative backdoor attack in a decentralized reinforcement learning scenario. Differing from the existing methods that hide a whole backdoor attack behind their shared policies, our method decomposes the backdoor behavior into multiple components according to the state space of RL. Each malicious agent hides one component in its policy and shares its policy with the benign agents. When a benign agent learns all the poisoned policies, the backdoor attack is assembled in its policy. The theoretical proof is given to show that our cooperative method can successfully inject the backdoor into the RL policies of benign agents. Compared with the existing backdoor attacks, our cooperative method is more covert since the policy from each attacker only contains a component of the backdoor attack and is harder to detect. Extensive simulations are conducted based on Atari environments to demonstrate the efficiency and covertness of our method. To the best of our knowledge, this is the first paper presenting a provable cooperative backdoor attack in decentralized reinforcement learning.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 22 of its 39 references that are in the map. First posted on arXiv 24 May 2024.

Builds on

22 of 39 references.

References · 22

  1. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  2. 2018How To Backdoor Federated Learningcited by 765
  3. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  4. 2020Safe Reinforcement Learning in Constrained Markov Decision Processescited by 115
  5. 2019Deep Reinforcement Learning for Cyber Securitycited by 95
  6. 2021CRFL: Certifiably Robust Federated Learning against Backdoor Attackscited by 91
  7. 2021BACKDOORL: Backdoor Attack against Competitive Reinforcement Learningcited by 68
  8. 2023BadRL: Sparse Targeted Backdoor Attack Against Reinforcement Learningcited by 30
  9. 2023Safe Offline Reinforcement Learning with Real-Time Budget Constraintscited by 28
  10. 2022BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasetscited by 25
  11. 2021Reinforcement Learning for IoT Security: A Comprehensive Surveycited by 23
  12. 2023MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimizationcited by 20
10 more
  1. 2022Provable Defense against Backdoor Policies in Reinforcement Learningcited by 18
  2. 2024Modeling Other Players with Bayesian Beliefs for Games with Incomplete Informationcited by 17
  3. 2024Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learningcited by 16
  4. 2019Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Informationcited by 13
  5. 2022Value Functions Factorization with Latent State Information Sharing in Decentralized Multi-Agent Policy Gradientscited by 12
  6. 2022A Bayesian Optimization Framework for Finding Local Optima in Expensive Multi-Modal Functionscited by 12
  7. 2023Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agentscited by 12
  8. 2023Real-time Network Intrusion Detection via Decision Transformerscited by 12
  9. 2022Coordinate-Aligned Multi-Camera Collaboration for Active Multi-Object Trackingcited by 7
  10. 2024Collaborative AI Teaming in Unknown Environments via Active Goal Deductioncited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 2; 2026: 1.

6 papers.

  1. 2024Learning from Random Demonstrations: Offline Reinforcement Learning with Importance-Sampled Diffusion Modelscited by 8
  2. 2025A Neurosymbolic Framework for Interpretable Cognitive Attack Detection in Augmented Realitycited by 8
  3. 2026Cochain Perspectives on Temporal-Difference Signals for Learning Beyond Markov Dynamicscited by 5
  4. 2025Tail-Risk-Safe Monte Carlo Tree Search under PAC-Level Guaranteescited by 4
  5. 2024A Resource-Adaptive Approach for Federated Learning under Resource-Constrained Environmentscited by 1
  6. 2024Federating to Grow Transformers with Constrained Resources without Model Sharingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024A Spatiotemporal Stealthy Backdoor Attack against Cooperative Multi-Agent Deep Reinforcement Learning
  2. 2025Exposing Vulnerabilities in RL: A Novel Stealthy Backdoor Attack through Reward Poisoning ↗
  3. 2022PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning
  4. 2025Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning
  5. 2025PNAct: Crafting Backdoor Attacks in Safe Reinforcement Learning
  6. 2025BLAST: A Stealthy Backdoor Leverage Attack against Cooperative Multi-Agent Deep Reinforcement Learning based Systems
  7. 2022Backdoor Attacks on Multiagent Collaborative Systems
  8. 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents