Data to 7 Oct 2026

Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks

arXiv 1701.04143 ↗First posted 16 Jan 2017cs.LG cs.AIcited by 91

Not on the map. Why?

Abstract (arXiv)

Deep learning classifiers are known to be inherently vulnerable to manipulation by intentionally perturbed inputs, named adversarial examples. In this work, we establish that reinforcement learning techniques based on Deep Q-Networks (DQNs) are also vulnerable to adversarial input perturbations, and verify the transferability of adversarial examples across different DQN models. Furthermore, we present a novel class of attacks based on this vulnerability that enable policy manipulation and induction in the learning process of DQNs. We propose an attack mechanism that exploits the transferability of adversarial examples to implement policy induction attacks on DQNs, and demonstrate its efficacy and impact through experimental study of a game-learning scenario.

Key facts. Cited by 91 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jan 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 25; 2022: 21; 2023: 9; 2024: 14; 2025: 13; 2026: 8.

91 papers.

Sort:

By area:

2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 133
2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
2022RORL: Robust Offline Reinforcement Learning via Conservative Smoothingcited by 83
2021Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RLcited by 54
2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 42
2021CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothingcited by 41
2021Policy Smoothing for Provably Robust Reinforcement Learningcited by 39
2022Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizabilitycited by 32
2021Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learningcited by 29
2021Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environmentscited by 26
2022Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learningcited by 21

38 more

2022Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learningcited by 21
2022What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?cited by 21
2021Center Smoothing: Certified Robustness for Networks with Structured Outputscited by 18
2023Towards more Practical Threat Models in Artificial Intelligence Securitycited by 17
2021Neural Network Verification in Controlcited by 14
2021Understanding Adversarial Attacks on Observations in Deep Reinforcement Learningcited by 13
2021Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patternscited by 13
2023Optimal Attack and Defense for Reinforcement Learningcited by 12
2021MDPFuzz: Testing Models Solving Markov Decision Processescited by 11
2021Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPScited by 10
2021Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defensescited by 9
2021SoK: Machine Learning Governancecited by 9
2022Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learningcited by 9
2023Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learningcited by 9
2022Sparse Adversarial Attack in Multi-agent Reinforcement Learningcited by 8
2024Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policiescited by 8
2022Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learningcited by 7
2022New Challenges in Reinforcement Learning: A Survey of Security and Privacycited by 7
2024SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systemscited by 7
2025Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Drivingcited by 7
2026WMAttack: Automated Attack Search for Adversarial Evaluation of World-Model Agentscited by 6
2021Improving the Transferability of Adversarial Examples with New Iteration Framework and Input Dropoutcited by 5
2022Deep-Attack over the Deep Reinforcement Learningcited by 5
2022Reward Delay Attacks on Deep Reinforcement Learningcited by 5
2023Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learningcited by 5
2025UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learningcited by 5
2021Disturbing Reinforcement Learning Agents with Corrupted Rewardscited by 4
2021Balancing detectability and performance of attacks on the control channel of Markov Decision Processescited by 4
2024Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-errorcited by 4
2024Data Poisoning Attacks on Off-Policy Policy Evaluation Methodscited by 4
2024Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantizationcited by 4
2021Improving Robustness of Deep Reinforcement Learning Agents: Environment Attack based on the Critic Networkcited by 3
2021Efficient Action Poisoning Attacks on Linear Contextual Banditscited by 3
2022Truly Deterministic Policy Optimizationcited by 3
2022Emerging Threats in Deep Learning-Based Autonomous Driving: A Comprehensive Surveycited by 3
2023SoK: Adversarial Machine Learning Attacks and Defences in Multi-Agent Reinforcement Learningcited by 3
2025Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approachcited by 3
2021Towards Resilient Artificial Intelligence: Survey and Research Issuescited by 2

50 most cited of 91 All 91 (JSON)