mlsanityData to 14 Oct 2026

Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses

arXiv 2510.20314 ↗First posted 23 Oct 2025cs.CR cs.AI cs.LGcited by 2

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

Abstract (arXiv)

With the wide application of deep reinforcement learning (DRL) techniques in complex fields such as autonomous driving, intelligent manufacturing, and smart healthcare, how to improve its security and robustness in dynamic and changeable environments has become a core issue in current research. Especially in the face of adversarial attacks, DRL may suffer serious performance degradation or even make potentially dangerous decisions, so it is crucial to ensure their stability in security-sensitive scenarios. In this paper, we first introduce the basic framework of DRL and analyze the main security challenges faced in complex and changing environments. In addition, this paper proposes an adversarial attack classification framework based on perturbation type and attack target and reviews the mainstream adversarial attack methods against DRL in detail, including various attack methods such as perturbation state space, action space, reward function and model space. To effectively counter the attacks, this paper systematically summarizes various current robustness training strategies, including adversarial training, competitive training, robust learning, adversarial detection, defense distillation and other related defense techniques, we also discuss the advantages and shortcomings of these methods in improving the robustness of DRL. Finally, this paper looks into the future research direction of DRL in adversarial environments, emphasizing the research needs in terms of improving generalization, reducing computational complexity, and enhancing scalability and explainability, aiming to provide valuable references and directions for researchers.

Key facts. Cited by 2 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 53 of its 108 references that are in the map. First posted on arXiv 23 Oct 2025.

Builds on

53 of 108 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning20 Nov
  2. 2024Stealthy Imitation: Reward-guided Environment-free Policy Stealing11 May

Other references · 51

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  3. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  4. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  5. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,103
  6. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  7. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 786
  8. 2016Universal adversarial perturbationscited by 784
  9. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
  10. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 721
  11. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  12. 2017Robust Adversarial Reinforcement Learningcited by 451
38 more
  1. 2018Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Networkcited by 420
  2. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
  3. 2017Adversarial Attacks on Neural Network Policiescited by 320
  4. 2019Intrinsic dimension of data representations in deep neural networkscited by 282
  5. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 238
  6. 2023Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attackscited by 194
  7. 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 174
  8. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 135
  9. 2017Delving into adversarial attacks on deep policiescited by 104
  10. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  11. 2019Distilling Policy Distillationcited by 84
  12. 2018Reinforcement Learning with Perturbed Rewardscited by 79
  13. 2020Robust Deep Reinforcement Learning through Adversarial Losscited by 75
  14. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 67
  15. 2020Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learningcited by 61
  16. 2016Defensive Distillation is Not Robust to Adversarial Examplescited by 60
  17. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 48
  18. 2023RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Modelscited by 32
  19. 2019Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agentscited by 25
  20. 2020Stealing Deep Reinforcement Learning Models for Fun and Profitcited by 24
  21. 2021Defense Against Reward Poisoning Attacks in Reinforcement Learningcited by 21
  22. 2022Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learningcited by 20
  23. 2021Understanding Adversarial Attacks on Observations in Deep Reinforcement Learningcited by 13
  24. 2021Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observationscited by 12
  25. 2021Training a Resilient Q-Network against Observational Interferencecited by 9
  26. 2021Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defensescited by 9
  27. 2024System-level Analysis of Adversarial Attacks and Defenses on Intelligence in O-RAN based Cellular Networkscited by 8
  28. 2018Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noisecited by 7
  29. 2023Local Environment Poisoning Attacks on Federated Reinforcement Learningcited by 6
  30. 2023ReRoGCRL: Representation-based Robustness in Goal-Conditioned Reinforcement Learningcited by 6
  31. 2022Reward Delay Attacks on Deep Reinforcement Learningcited by 5
  32. 2020Adversary Agnostic Robust Deep Reinforcement Learningcited by 4
  33. 2024Universal Black-Box Reward Poisoning Attack against Offline Reinforcement Learningcited by 4
  34. 2024Safe and Robust Reinforcement Learning: Principles and Practicecited by 4
  35. 2022Deep Reinforcement Learning based Evasion Generative Adversarial Network for Botnet Detectioncited by 3
  36. 2023Enhancing the Robustness of QMIX against State-adversarial Attackscited by 3
  37. 2025A Trust-Aware and Cost-Optimized Blockchain Oracle Selection Model with Deep Reinforcement Learningcited by 2
  38. 2024Reinforcement Learning-Based Approaches for Enhancing Security and Resilience in Smart Control: A Survey on Attack and Defense Methodscited by 1

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Adapting Noise-Driven PUF and AI for Secure WBG ICS: A Proof-of-Concept Studycited by 0
  2. 2026Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Drivingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey
  2. 2025Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach
  3. 2024Analyzing Adversarial Inputs in Deep Reinforcement Learning
  4. 2025A Framework for Adversarial Analysis of Decision Support Systems Prior to Deployment
  5. 2024Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
  6. 2025Sharpening the Spear: Adaptive Expert-Guided Adversarial Attack Against DRL-based Autonomous Driving Policies
  7. 2024Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
  8. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning