mlsanityData to 7 Oct 2026

Delving into adversarial attacks on deep policies

arXiv 1705.06452 ↗First posted 18 May 2017stat.ML cs.LGcited by 104

Not on the map. Why?

Abstract (arXiv)

Adversarial examples have been shown to exist for a variety of deep learning architectures. Deep reinforcement learning has shown promising results on training agent policies directly on raw inputs such as image pixels. In this paper we present a novel study into adversarial attacks on deep reinforcement learning polices. We compare the effectiveness of the attacks using adversarial examples vs. random noise. We present a novel method for reducing the number of times adversarial examples need to be injected for a successful attack, based on the value function. We further explore how re-training on random noise and FGSM perturbations affects the resilience against adversarial examples.

Key facts. Cited by 104 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 27; 2023: 18; 2024: 15; 2025: 12; 2026: 8.

104 papers.

Sort:

By area:

  1. 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 743
  2. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 133
  3. 2021Online Robust Reinforcement Learning with Model Uncertaintycited by 95
  4. 2022Policy Gradient Method For Robust Reinforcement Learningcited by 67
  5. 2021Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RLcited by 54
  6. 2022Sound Adversarial Audio-Visual Navigationcited by 46
  7. 2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 42
  8. 2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 41
  9. 2022On the Robustness of Safe Reinforcement Learning under Observational Perturbationscited by 38
  10. 2023Robust Multi-Agent Reinforcement Learning with State Uncertaintycited by 35
  11. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  12. 2021Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defensescited by 29
38 more
  1. 2021Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learningcited by 29
  2. 2021Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environmentscited by 26
  3. 2022COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attackscited by 25
  4. 2023Robust Average-Reward Markov Decision Processescited by 22
  5. 2022Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learningcited by 21
  6. 2022What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?cited by 21
  7. 2023Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustnesscited by 18
  8. 2023Stabilizing Unsupervised Environment Design with a Learned Adversarycited by 17
  9. 2022Adversarial Cheap Talkcited by 16
  10. 2023Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influencecited by 16
  11. 2021Investigating Vulnerabilities of Deep Neural Policiescited by 15
  12. 2022Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculumcited by 15
  13. 2022Robust Constrained Reinforcement Learningcited by 14
  14. 2022Are AlphaZero-like Agents Robust to Adversarial Perturbations?cited by 14
  15. 2023Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attackscited by 14
  16. 2021Multi-Task Federated Reinforcement Learning with Adversariescited by 13
  17. 2021Understanding Adversarial Attacks on Observations in Deep Reinforcement Learningcited by 13
  18. 2021Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patternscited by 13
  19. 2022A Search-Based Testing Approach for Deep Reinforcement Learning Agentscited by 12
  20. 2023Optimal Attack and Defense for Reinforcement Learningcited by 12
  21. 2021MDPFuzz: Testing Models Solving Markov Decision Processescited by 11
  22. 2021Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPscited by 11
  23. 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPScited by 10
  24. 2021Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defensescited by 9
  25. 2021Controlled Caption Generation for Images Through Adversarial Attackscited by 9
  26. 2022Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learningcited by 9
  27. 2023Adjustable Robust Reinforcement Learning for Online 3D Bin Packingcited by 9
  28. 2022Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoisingcited by 8
  29. 2024A Survey Analyzing Generalization in Deep Reinforcement Learningcited by 8
  30. 2024Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policiescited by 8
  31. 2022Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learningcited by 7
  32. 2021Network Defense is Not a Gamecited by 6
  33. 2023Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisionscited by 6
  34. 2023ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learningcited by 6
  35. 2021How Private Is Your RL Policy? An Inverse RL Based Analysis Frameworkcited by 5
  36. 2022Deep-Attack over the Deep Reinforcement Learningcited by 5
  37. 2022Reward Delay Attacks on Deep Reinforcement Learningcited by 5
  38. 2024Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defensescited by 5

50 most cited of 104 All 104 (JSON)