mlsanityData to 7 Oct 2026

Tactics of Adversarial Attack on Deep Reinforcement Learning Agents

arXiv 1703.06748 ↗First posted 8 Mar 2017cs.LG cs.CR stat.MLcited by 163

Not on the map. Why?

Abstract (arXiv)

We introduce two tactics to attack agents trained by deep reinforcement learning algorithms using adversarial examples, namely the strategically-timed attack and the enchanting attack. In the strategically-timed attack, the adversary aims at minimizing the agent's reward by only attacking the agent at a small subset of time steps in an episode. Limiting the attack activity to this subset helps prevent detection of the attack by the agent. We propose a novel method to determine when an adversarial example should be crafted and applied. In the enchanting attack, the adversary aims at luring the agent to a designated target state. This is achieved by combining a generative model and a planning algorithm: while the generative model predicts the future states, the planning algorithm generates a preferred sequence of actions for luring the agent. A sequence of adversarial examples is then crafted to lure the agent to take the preferred sequence of actions. We apply the two tactics to the agents trained by the state-of-the-art deep reinforcement learning algorithm including DQN and A3C. In 5 Atari games, our strategically timed attack reduces as much reward as the uniform attack (i.e., attacking at every time step) does by attacking the agent 4 times less often. Our enchanting attack lures the agent toward designated target states with a more than 70% success rate. Videos are available at http://yenchenlin.me/adversarial_attack_RL/

Key facts. Cited by 163 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 38; 2022: 32; 2023: 27; 2024: 26; 2025: 21; 2026: 18.

163 papers.

Sort:

By area:

  1. 2022Scaling Laws for Reward Model Overoptimizationcited by 1,056
  2. 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examplescited by 163
  3. 2024Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithmscited by 139
  4. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 133
  5. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  6. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 115
  7. 2021Online Robust Reinforcement Learning with Model Uncertaintycited by 95
  8. 2022Policy Gradient Method For Robust Reinforcement Learningcited by 67
  9. 2021BACKDOORL: Backdoor Attack against Competitive Reinforcement Learningcited by 66
  10. 2021Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RLcited by 54
  11. 2022Sound Adversarial Audio-Visual Navigationcited by 46
  12. 2022Uncertainty Quantification of Collaborative Detection for Self-Drivingcited by 46
38 more
  1. 2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 41
  2. 2022On the Robustness of Safe Reinforcement Learning under Observational Perturbationscited by 38
  3. 2021TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothnesscited by 37
  4. 2023Robust Multi-Agent Reinforcement Learning with State Uncertaintycited by 35
  5. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  6. 2021Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defensescited by 29
  7. 2021Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learningcited by 29
  8. 2021Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environmentscited by 26
  9. 2022Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policiescited by 22
  10. 2023Robust Average-Reward Markov Decision Processescited by 22
  11. 2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 22
  12. 2022Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learningcited by 21
  13. 2022Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learningcited by 21
  14. 2022What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?cited by 21
  15. 2021Defense Against Reward Poisoning Attacks in Reinforcement Learningcited by 20
  16. 2021A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directionscited by 19
  17. 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agentscited by 19
  18. 2021Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learningcited by 18
  19. 2023Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustnesscited by 18
  20. 2023Stabilizing Unsupervised Environment Design with a Learned Adversarycited by 17
  21. 2023Towards more Practical Threat Models in Artificial Intelligence Securitycited by 17
  22. 2024Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policiescited by 17
  23. 2023Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influencecited by 16
  24. 2023Towards Reasonable Budget Allocation in Untargeted Graph Structure Attacks via Gradient Debiascited by 16
  25. 2024RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviorscited by 16
  26. 2021Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentationcited by 15
  27. 2022Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculumcited by 15
  28. 2022Robust Constrained Reinforcement Learningcited by 14
  29. 2022Are AlphaZero-like Agents Robust to Adversarial Perturbations?cited by 14
  30. 2023Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attackscited by 14
  31. 2021Multi-Task Federated Reinforcement Learning with Adversariescited by 13
  32. 2021Understanding Adversarial Attacks on Observations in Deep Reinforcement Learningcited by 13
  33. 2021Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patternscited by 13
  34. 2022Rare event failure test case generation in Learning-Enabled-Controllerscited by 13
  35. 2021Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Modelscited by 12
  36. 2022A Search-Based Testing Approach for Deep Reinforcement Learning Agentscited by 12
  37. 2023Testing of Deep Reinforcement Learning Agents with Surrogate Modelscited by 12
  38. 2023Optimal Attack and Defense for Reinforcement Learningcited by 12

50 most cited of 163 All 163 (JSON)