Provable Defense against Backdoor Policies in Reinforcement Learning

18 November 2022

Papers citing "Provable Defense against Backdoor Policies in Reinforcement Learning"

9 / 9 papers shown

Title
Backdoors in DRL: Four Environments Focusing on In-distribution Triggers C. Ashcraft Ted Staley Josh Carney Cameron Hickert Derek Juba Kiran Karra AAML 58 0 0 22 May 2025
Adversarial Inception Backdoor Attacks against Reinforcement Learning Ethan Rathbun Christopher Amato Alina Oprea AAML 55 0 0 17 Oct 2024
Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space Sanyam Vyas Chris Hicks V. Mavroudis AAML 78 0 0 21 Jul 2024
Cooperative Backdoor Attack in Decentralized Reinforcement Learning with Theoretical Guarantee Mengtong Gao Yifei Zou Zuyuan Zhang Xiuzhen Cheng Dongxiao Yu AAML 100 4 0 24 May 2024
Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations Xiaolin Sun Zizhan Zheng OnRL 75 1 0 06 Mar 2024
Reinforcement Learning-Based Approaches for Enhancing Security and Resilience in Smart Control: A Survey on Attack and Defense Methods Zheyu Zhang AAML 47 0 0 23 Feb 2024
Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error Haoran Li Zicheng Zhang Wang Luo Congying Han Yudong Hu Tiande Guo Shichen Liao AAML 135 2 0 03 Feb 2024
BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets Chen Gong Zhou Yang Yunru Bai Junda He Jieke Shi ... Arunesh Sinha Bowen Xu Xinwen Hou David Lo Guoliang Fan AAML OffRL 95 13 0 07 Oct 2022
PolicyCleanse: Backdoor Detection and Mitigation in Reinforcement Learning Junfeng Guo Ang Li Cong Liu AAML 129 17 0 08 Feb 2022