Jun Guo
6 Papers
11 Citations
Jun Guo is an academic researcher. The author has contributed to research in topics: Computer science. The author has an hindex of 3, co-authored 4 publications.
Chat about Author
Papers
Towards Comprehensive Testing on the Robustness of Cooperative Multi-agent Reinforcement Learning
Jun Guo,Yonghong Chen,Yihang Hao,Zixin Yin,Yin Yu,Simin Li +5 more
- 17 Apr 2022
TL;DR: The first robustness testing framework for c-MARL algorithms, motivated by Markov Decision Process, MARLSafe considers the robustness of c- MARL algorithms comprehensively from three aspects, namely state robustness, action robustness and reward robustness.
Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
TL;DR: In this paper , a black-box attack called Adversarial Minority Influence (AMI) is proposed for cooperative multi-agent reinforcement learning (c-MARL) under adversarial attacks, which can be launched without knowing victim parameters.
Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attacks
Jun Guo,Xingyu Zheng,Aishan Liu,Siyuan Liang,Yisong Xiao,Yichao Wu,Xiangdong Liu +6 more
- 02 Aug 2023
TL;DR: This paper proposes Isolation and Induction (InI), a novel and effective training framework for model stealing defenses that directly trains a defensive model by isolating the adversary's training gradient from the expected gradient, which can effectively reduce the inference computational cost.
MIR2: Towards Provably Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization
Simin Li,Ruixiao Xu,Jun Guo,Pu Feng,Jiakai Wang,Aishan Liu,Yaodong Yang,Xianglong Liu,Weifeng Lv +8 more
TL;DR: This work frames robustness as an inference problem and proves that minimizing mutual information between histories and actions implicitly maximizes a lower bound on robustness under certain assumptions, and proposes MIR2, which trains policy in routine scenarios and minimize Mutual Information as Robust Regularization.
Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game
TL;DR: In this paper , a Bayesian Adversarial Robust Dec-POMDP framework is proposed to address the uncertainty that any agent can be adversarial, which views Byzantine adversaries as nature-dictated types, represented by a separate transition.