mlsanityData to 7 Oct 2026

Certified Adversarial Robustness for Deep Reinforcement Learning

arXiv 1910.12908 ↗First posted 28 Oct 2019cs.RO cs.AI cs.LGcited by 47

Not on the map. Why?

Abstract (arXiv)

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs (from noise or adversarial examples) are often enough to change network-based decisions, which was already shown to cause an autonomous vehicle to swerve into oncoming traffic. In light of these dangers, numerous algorithms have been developed as defensive mechanisms from these adversarial inputs, some of which provide formal robustness guarantees or certificates. This work leverages research on certified adversarial robustness to develop an online certified defense for deep reinforcement learning algorithms. The proposed defense computes guaranteed lower bounds on state-action values during execution to identify and choose the optimal action under a worst-case deviation in input space due to possible adversaries or noise. The approach is demonstrated on a Deep Q-Network policy and is shown to increase robustness to noise and adversaries in pedestrian collision avoidance scenarios and a classic control task.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 12; 2023: 8; 2024: 8; 2025: 5; 2026: 4.

47 papers.

Sort:

By area:

  1. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  2. 2021Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RLcited by 54
  3. 2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 42
  4. 2021Policy Smoothing for Provably Robust Reinforcement Learningcited by 39
  5. 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 36
  6. 2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
  7. 2021A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directionscited by 19
  8. 2021ROMAX: Certifiably Robust Deep Multiagent Reinforcement Learning via Convex Relaxationcited by 17
  9. 2024RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviorscited by 16
  10. 2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPScited by 10
  11. 2021Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurancecited by 8
  12. 2022Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systemscited by 7
35 more
  1. 2022Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learningcited by 7
  2. 2023Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RLcited by 7
  3. 2025Position: Certified Robustness Does Not (Yet) Imply Model Securitycited by 4
  4. 2021Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learningcited by 3
  5. 2022A Verification Framework for Certifying Learning-Based Safety-Critical Aviation Systemscited by 3
  6. 2022How to Enable Uncertainty Estimation in Proximal Policy Optimizationcited by 3
  7. 2023Regret-Based Defense in Adversarial Reinforcement Learningcited by 3
  8. 2023Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policycited by 3
  9. 2023Robustness Verification for Knowledge-Based Logic of Risky Driving Scenescited by 3
  10. 2024Achieving Domain-Independent Certified Robustness via Knowledge Continuitycited by 3
  11. 2025Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approachcited by 3
  12. 2022Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learningcited by 2
  13. 2022Deep Reinforcement Learning with Vector Quantized Encodingcited by 2
  14. 2023Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretationcited by 2
  15. 2023Wasserstein Distributionally Robust Control Barrier Function using Conditional Value-at-Risk with Differentiable Convex Programmingcited by 2
  16. 2024Specification Overfitting in Artificial Intelligencecited by 2
  17. 2024On Minimizing Adversarial Counterfactual Error in Adversarial RLcited by 2
  18. 2026Robust Adversarial Policy Optimization Under Dynamics Uncertaintycited by 2
  19. 2026Diagnosing JEPA World Models with Action-Conditioned Predictive Consistencycited by 2
  20. 2021Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Rewardcited by 1
  21. 2022Red Teaming with Mind Reading: White-Box Adversarial Policies Against RL Agentscited by 1
  22. 2022Security of Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 1
  23. 2024Gradient Boosting Reinforcement Learningcited by 1
  24. 2025CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximizationcited by 1
  25. 2026TCRL: Temporal-Coupled Adversarial Training for Robust Constrained Reinforcement Learning in Worst-Case Scenarioscited by 1
  26. 2022Hysteresis-Based RL: Robustifying Reinforcement Learning-based Control Policies via Hybrid Controlcited by 0
  27. 2022Certifying Safety in Reinforcement Learning under Adversarial Perturbation Attackscited by 0
  28. 2023Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbationscited by 0
  29. 2023Robustness Verification of Deep Reinforcement Learning Based Control Systems using Reward Martingalescited by 0
  30. 2024Adaptive Discounting of Training Time Attackscited by 0
  31. 2024Training Verifiably Robust Agents Using Set-Based Reinforcement Learningcited by 0
  32. 2024Optimizing Sensor Redundancy in Sequential Decision-Making Problemscited by 0
  33. 2025Towards Robust Deep Reinforcement Learning against Environmental State Perturbationcited by 0
  34. 2025Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasetscited by 0
  35. 2026Certifying Lower Bounds for Risk-Sensitive Reinforcement Learning under Adversarial State Perturbationscited by 0