mlsanityData to 7 Oct 2026

New Challenges in Reinforcement Learning: A Survey of Security and Privacy

arXiv 2301.00188 ↗First posted 31 Dec 2022cs.LG cs.AI cs.CRcited by 7

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning (RL) is one of the most important branches of AI. Due to its capacity for self-adaption and decision-making in dynamic environments, reinforcement learning has been widely applied in multiple areas, such as healthcare, data markets, autonomous driving, and robotics. However, some of these applications and systems have been shown to be vulnerable to security or privacy attacks, resulting in unreliable or unstable services. A large number of studies have focused on these security and privacy problems in reinforcement learning. However, few surveys have provided a systematic review and comparison of existing problems and state-of-the-art solutions to keep up with the pace of emerging threats. Accordingly, we herein present such a comprehensive review to explain and summarize the challenges associated with security and privacy in reinforcement learning from a new perspective, namely that of the Markov Decision Process (MDP). In this survey, we first introduce the key concepts related to this area. Next, we cover the security and privacy issues linked to the state, action, environment, and reward function of the MDP process, respectively. We further highlight the special characteristics of security and privacy methodologies related to reinforcement learning. Finally, we discuss the possible future research directions within this area.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 42 of its 91 references that are in the map. First posted on arXiv 31 Dec 2022.

Builds on

42 of 91 references.

References · 42

  1. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  2. 2019Model-Based Reinforcement Learning for Ataricited by 495
  3. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 485
  4. 2017A Brief Survey of Deep Reinforcement Learningcited by 466
  5. 2017Robust Adversarial Reinforcement Learningcited by 439
  6. 2019Reinforcement Learning in Healthcare: A Surveycited by 308
  7. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progresscited by 294
  8. 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 167
  9. 2018Applications of Deep Reinforcement Learning in Communications and Networking: A Surveycited by 163
  10. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  11. 2020Adaptive Reward-Poisoning Attacks against Reinforcement Learningcited by 86
  12. 2020Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learningcited by 81
30 more
  1. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  2. 2017Virtual to Real Reinforcement Learning for Autonomous Drivingcited by 79
  3. 2020Stealthy and Efficient Adversarial Attacks against Deep Reinforcement Learningcited by 62
  4. 2020Private Reinforcement Learning with PAC and Regret Guaranteescited by 51
  5. 2019Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signalscited by 50
  6. 2020On the Robustness of Cooperative Multi-Agent Reinforcement Learningcited by 39
  7. 2019Deep Reinforcement Learning for Autonomous Internet of Things: Model, Applications and Challengescited by 36
  8. 2017Learning to Fly by Crashingcited by 33
  9. 2013On the Complexity of Solving Markov Decision Problemscited by 31
  10. 2019Privacy-preserving Q-Learning with Functional Noise in Continuous State Spacescited by 29
  11. 2019How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learningcited by 29
  12. 2020When Deep Reinforcement Learning Meets Federated Learning: Intelligent Multi-Timescale Resource Management for Multi-access Edge Computing in 5G Ultra Dense Networkcited by 29
  13. 2018Inverse reinforcement learning for video gamescited by 26
  14. 2022One Parameter Defense -- Defending against Data Inference Attacks via Differential Privacycited by 26
  15. 2019Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agentscited by 24
  16. 2020Policy Teaching in Reinforcement Learning via Environment Poisoning Attackscited by 24
  17. 2019Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimizationcited by 23
  18. 2021Differentially Private Regret Minimization in Episodic Markov Decision Processescited by 23
  19. 2020More Than Privacy: Applying Differential Privacy in Key Areas of Artificial Intelligencecited by 22
  20. 2018Dialogue Generation: From Imitation Learning to Inverse Reinforcement Learningcited by 21
  21. 2021Reinforcement Learning for IoT Security: A Comprehensive Surveycited by 21
  22. 2021Deceptive Reinforcement Learning for Privacy-Preserving Planningcited by 14
  23. 2019Blackbox Attacks on Reinforcement Learning Agents Using Approximated Temporal Informationcited by 13
  24. 2021Distributed Reinforcement Learning for Privacy-Preserving Dynamic Edge Cachingcited by 10
  25. 2020Falsification-Based Robust Adversarial Reinforcement Learningcited by 6
  26. 2020Differential Advising in Multi-Agent Reinforcement Learningcited by 6
  27. 2021How Private Is Your RL Policy? An Inverse RL Based Analysis Frameworkcited by 5
  28. 2020A Differentially Private Game Theoretic Approach for Deceiving Cyber Adversariescited by 4
  29. 2020Differentially Private Multi-Agent Planning for Logistic-like Problemscited by 4
  30. 2022Policy Learning for Robust Markov Decision Process with a Mismatched Generative Modelcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 0; 2026: 3.

7 papers.

  1. 2026SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecuritycited by 4
  2. 2024Strategizing against Q-learners: A Control-theoretical Approachcited by 1
  3. 2024Task-agnostic Decision Transformer for Multi-type Agent Control with Federated Split Trainingcited by 1
  4. 2024AI Ethics by Design: Implementing Customizable Guardrails for Responsible AI Developmentcited by 1
  5. 2024Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learningcited by 0
  6. 2026Randomized Least Squares Value Iteration itself is Joint Differentially Privatecited by 0
  7. 2026Privacy-Aware Agent Collaboration for Dynamic VR Slice Management in 6G SD-RANcited by 0