Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Huan Zhang

Huan Zhang

Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness

Jun 15, 2022
Tianlong Chen, Huan Zhang, Zhenyu Zhang, Shiyu Chang, Sijia Liu, Pin-Yu Chen, Zhangyang Wang

Figure 1 for Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness

Figure 2 for Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness

Figure 3 for Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness

Figure 4 for Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness

* Accepted by ICML 2022

Access Paper or Ask Questions

On the Robustness of Safe Reinforcement Learning under Observational Perturbations

May 29, 2022
Zuxin Liu, Zijian Guo, Zhepeng Cen, Huan Zhang, Jie Tan, Bo Li, Ding Zhao

Figure 1 for On the Robustness of Safe Reinforcement Learning under Observational Perturbations

Figure 2 for On the Robustness of Safe Reinforcement Learning under Observational Perturbations

Figure 3 for On the Robustness of Safe Reinforcement Learning under Observational Perturbations

Figure 4 for On the Robustness of Safe Reinforcement Learning under Observational Perturbations

* 27 pages, 3 figures, 3 tables

Access Paper or Ask Questions

COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

Mar 16, 2022
Fan Wu, Linyi Li, Chejian Xu, Huan Zhang, Bhavya Kailkhura, Krishnaram Kenthapadi, Ding Zhao, Bo Li

Figure 1 for COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

Figure 2 for COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

Figure 3 for COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

Figure 4 for COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks

* Published as a conference paper at ICLR 2022

Access Paper or Ask Questions

Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training

Oct 19, 2021
Alexander Pan, Yongkyun Lee, Huan Zhang, Yize Chen, Yuanyuan Shi

Figure 1 for Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training

Figure 2 for Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training

Figure 3 for Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training

Figure 4 for Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training

* Published at 2021 ICML RL4RL Workshop; Submitted to 2022 PSCC

Access Paper or Ask Questions