activity
20162023
most citedFast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers

60 citations · 190 across the 15 of their papers we have counts for

collaborators
Showing cs.LGShow all

18 papers · 1 filter

cs.LG2023★ 3 cited

Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories

Li-Cheng Lan, Huan Zhang, Cho-Jui Hsieh

In this paper, we define, evaluate, and improve the ``relay-generalization'' performance of reinforcement learning (RL) agents on the out-of-distribution ``controllable'' states. I…

cs.LG2022★ 8 cited

Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation

Zhouxing Shi, Yihan Wang, Huan Zhang +2

Lipschitz constants are connected to many properties of neural networks, such as robustness, fairness, and generalization. Existing methods for computing Lipschitz constants either…

cs.LG2022★ 33 cited

General Cutting Planes for Bound-Propagation-Based Neural Network Verification

Huan Zhang, Shiqi Wang, Kaidi Xu +5

Bound propagation methods, when combined with branch and bound, are among the most effective methods to formally verify properties of deep neural networks such as correctness, robu…

cs.LG2022★ 9 cited

On the Robustness of Safe Reinforcement Learning under Observational Perturbations

Zuxin Liu, Zijian Guo, Zhepeng Cen +4

Safe reinforcement learning (RL) trains a policy to maximize the task reward while satisfying safety constraints. While prior works focus on the performance optimality, we find tha…

cs.LG2022★ 1 cited

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

Fan Wu, Linyi Li, Chejian Xu +5

As reinforcement learning (RL) has achieved near human-level performance in a variety of tasks, its robustness has raised great attention. While a vast body of research has explore…

cs.LG2021★ 4 cited

Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds

Yujia Huang, Huan Zhang, Yuanyuan Shi +2

Certified robustness is a desirable property for deep neural networks in safety-critical applications, and popular training algorithms can certify robustness of a neural network by…