mlsanityData to 7 Oct 2026

Targeted Adversarial Attacks on Deep Reinforcement Learning Policies via Model Checking

arXiv 2212.05337 ↗First posted 10 Dec 2022cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Deep Reinforcement Learning (RL) agents are susceptible to adversarial noise in their observations that can mislead their policies and decrease their performance. However, an adversary may be interested not only in decreasing the reward, but also in modifying specific temporal logic properties of the policy. This paper presents a metric that measures the exact impact of adversarial attacks against such properties. We use this metric to craft optimal adversarial attacks. Furthermore, we introduce a model checking method that allows us to verify the robustness of RL policies against adversarial attacks. Our empirical analysis confirms (1) the quality of our metric to craft adversarial attacks against temporal logic properties, and (2) that we are able to concisely assess a system's robustness against attacks.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 35 of its 61 references that are in the map. First posted on arXiv 10 Dec 2022.

Builds on

35 of 61 references.

References · 35

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2016Concrete Problems in AI Safetycited by 1,582
  5. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  6. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  7. 2017Robust Adversarial Reinforcement Learningcited by 439
  8. 2017Adversarial Attacks on Neural Network Policiescited by 314
  9. 2016Safety Verification of Deep Neural Networkscited by 262
  10. 2020Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observationscited by 235
  11. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 209
  12. 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 163
23 more
  1. 2018Reachability Analysis of Deep Neural Networks with Provable Guaranteescited by 93
  2. 2020Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learningcited by 81
  3. 2018Omega-Regular Objectives in Model-Free Reinforcement Learningcited by 74
  4. 2017Environment-Independent Task Specifications via GLTLcited by 67
  5. 2020The Probabilistic Model Checker Stormcited by 64
  6. 2020Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learningcited by 61
  7. 2021Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)cited by 55
  8. 2014A Learning Based Approach to Control Synthesis of Markov Decision Processes for Linear Temporal Logic Specificationscited by 49
  9. 2022On the Robustness of Safe Reinforcement Learning under Observational Perturbationscited by 38
  10. 2019Reinforcement Learning with Probabilistic Guarantees for Autonomous Drivingcited by 27
  11. 2019Spatiotemporally Constrained Action Space Attacks on Deep Reinforcement Learning Agentscited by 24
  12. 2022COOL-MC: A Comprehensive Tool for Reinforcement Learning and Model Checkingcited by 19
  13. 2017Detecting Adversarial Attacks on Neural Network Policies with Visual Foresightcited by 17
  14. 2021Adversarial attacks in consensus-based multi-agent reinforcement learningcited by 17
  15. 2015Permissive Controller Synthesis for Probabilistic Systemscited by 16
  16. 2019Verifiably Safe Off-Model Reinforcement Learningcited by 16
  17. 2018Online Robust Policy Learning in the Presence of Unknown Adversariescited by 15
  18. 2020Query-based Targeted Action-Space Adversarial Policies on Deep Reinforcement Learning Agentscited by 15
  19. 2021Investigating Vulnerabilities of Deep Neural Policiescited by 15
  20. 2020Statistically Model Checking PCTL Specifications on Markov Decision Processes via Reinforcement Learningcited by 12
  21. 2021Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPscited by 11
  22. 2016Optimizing Expectation with Guarantees in POMDPs (Technical Report)cited by 7
  23. 2021Feature-Based Interpretable Reinforcement Learning based on State-Transition Modelscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2026Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MCcited by 3
  2. 2025Formal Verification of Noisy Quantum Reinforcement Learning Policiescited by 0
  3. 2026COOL-MC: Verifying and Explaining RL Policies for Platelet Inventory Managementcited by 0
  4. 2026COOL-MC: Verifying and Explaining RL Policies for Multi-bridge Network Maintenancecited by 0
  5. 2026Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policiescited by 0