activity
20172024
most citedThe Limitations of Adversarial Training and the Blind-Spot Attack

60 citations · 154 across the 11 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2024★ 1 cited

DriveGPT: Scaling Autoregressive Behavior Models for Driving

Xin Huang, Eric M. Wolff, Paul Vernaza +13

We present DriveGPT, a scalable behavior model for autonomous driving. We model driving as a sequential decision-making task, and learn a transformer model to predict future agent…

cs.LG2021★ 46 cited

Robust Reinforcement Learning on State Observations with Learned Optimal Adversary

Huan Zhang, Hongge Chen, Duane Boning +1

We study the robustness of reinforcement learning (RL) with adversarially perturbed state observations, which aligns with the setting of many adversarial attacks to deep reinforcem…

cs.LG2020★ 1 cited

On -norm Robustness of Ensemble Stumps and Trees

Yihan Wang, Huan Zhang, Hongge Chen +2

Recent papers have demonstrated that ensemble stumps and trees could be vulnerable to small input perturbations, so robustness verification and defense for those models have become…

cs.LG2020★ 4 cited

Multi-Stage Influence Function

Hongge Chen, Si Si, Yang Li +4

Multi-stage training and knowledge transfer, from a large-scale pretraining task to various finetuning tasks, have revolutionized natural language processing and computer vision re…

cs.LG2019

Towards Stable and Efficient Training of Verifiably Robust Neural Networks

Huan Zhang, Hongge Chen, Chaowei Xiao +5

Training neural networks with verifiable robustness guarantees is challenging. Several existing approaches utilize linear relaxation based neural network output bounds under pertur…

cs.LG2019

Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective

Kaidi Xu, Hongge Chen, Sijia Liu +4

Graph neural networks (GNNs) which apply the deep neural networks to graph data have achieved significant performance for the task of semi-supervised node classification. However,…