Policy Resilience to Environment Poisoning Attacks on Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
This paper investigates policy resilience to training-environment poisoning attacks on reinforcement learning (RL) policies, with the goal of recovering the deployment performance of a poisoned RL policy. Due to the fact that the policy resilience is an add-on concern to RL algorithms, it should be resource-efficient, time-conserving, and widely applicable without compromising the performance of RL algorithms. This paper proposes such a policy-resilience mechanism based on an idea of knowledge sharing. We summarize the policy resilience as three stages: preparation, diagnosis, recovery. Specifically, we design the mechanism as a federated architecture coupled with a meta-learning manner, pursuing an efficient extraction and sharing of the environment knowledge. With the shared knowledge, a poisoned agent can quickly identify the deployment condition and accordingly recover its policy performance. We empirically evaluate the resilience mechanism for both model-based and model-free RL algorithms, showing its effectiveness and efficiency in restoring the deployment performance of a poisoned policy.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 35 of its 46 references that are in the map. First posted on arXiv 24 Apr 2023.
Builds on
35 of 46 references.
References · 35
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
- 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
- 2019Federated Machine Learning: Concept and Applicationscited by 409
- 2017Adversarial Attacks on Neural Network Policiescited by 314
- 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 224
- 2019VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learningcited by 210
- 2018Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansioncited by 167
- 2020Privacy and Robustness in Federated Learning: Attacks and Defensescited by 163
23 more
- 2018Model-Based Value Estimation for Efficient Model-Free Reinforcement Learningcited by 152
- 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 133
- 2021Online and Offline Reinforcement Learning by Planning with a Learned Modelcited by 90
- 2020Adaptive Reward-Poisoning Attacks against Reinforcement Learningcited by 86
- 2020Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learningcited by 81
- 2017Virtual to Real Reinforcement Learning for Autonomous Drivingcited by 79
- 2019Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systemscited by 77
- 2018Reinforcement Learning with Perturbed Rewardscited by 76
- 2019Corruption-robust exploration in episodic reinforcement learningcited by 72
- 2019Policy Poisoning in Batch Reinforcement Learning and Controlcited by 70
- 2013Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizationscited by 68
- 2021A Model Selection Approach for Corruption Robust Reinforcement Learningcited by 45
- 2019Federated Transfer Reinforcement Learning for Autonomous Drivingcited by 43
- 2017Whatever Does Not Kill Deep Reinforcement Learning, Makes It Strongercited by 35
- 2021Robust Policy Gradient against Strong Data Corruptioncited by 30
- 2017Robust and Efficient Transfer Learning with Hidden-Parameter Markov Decision Processescited by 28
- 2022COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attackscited by 25
- 2020Generalized Hidden Parameter MDPs Transferable Model-based RL in a Handful of Trialscited by 20
- 2021Defense Against Reward Poisoning Attacks in Reinforcement Learningcited by 20
- 2021Improved Corruption Robust Algorithms for Episodic Reinforcement Learningcited by 20
- 2017Detecting Adversarial Attacks on Neural Network Policies with Visual Foresightcited by 17
- 2018Mitigation of Policy Manipulation Attacks on Deep Q-Networks with Parameter-Space Noisecited by 7
- 2021Challenges for Reinforcement Learning in Healthcarecited by 7
Built on by
Citing papers per year: 2025: 1.
1 paper.