149 citations · 563 across the 19 of their papers we have counts for
19 papers
Causal Composition Diffusion Model for Closed-loop Traffic Generation
Haohong Lin, Xin Huang, Tung Phan-Minh +6
Simulation is critical for safety evaluation in autonomous driving, particularly in capturing complex interactive behaviors. However, generating realistic and controllable traffic…
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…
Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-based Autonomous Driving
Yichen Xie, Hongge Chen, Gregory P. Meyer +6
Due to the lack of depth cues in images, multi-frame inputs are important for the success of vision-based perception, prediction, and planning in autonomous driving. Observations f…
SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors
Hongge Chen, Zhao Chen, Gregory P. Meyer +4
We present SHIFT3D, a differentiable pipeline for generating 3D shapes that are structurally plausible yet challenging to 3D object detectors. In safety-critical applications like…
Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving
Eli Bronstein, Mark Palatucci, Dominik Notz +14
We demonstrate the first large-scale application of model-based generative adversarial imitation learning (MGAIL) to the task of dense urban self-driving. We augment standard MGAIL…
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…
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…
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…
Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations
Huan Zhang, Hongge Chen, Chaowei Xiao +4
A deep reinforcement learning (DRL) agent observes its states through observations, which may contain natural measurement errors or adversarial noises. Since the observations devia…
Adversarial T-shirt! Evading Person Detectors in A Physical World
Kaidi Xu, Gaoyuan Zhang, Sijia Liu +6
It is known that deep neural networks (DNNs) are vulnerable to adversarial attacks. The so-called physical adversarial examples deceive DNN-based decisionmakers by attaching advers…
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…
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,…
Robustness Verification of Tree-based Models
Hongge Chen, Huan Zhang, Si Si +3
We study the robustness verification problem for tree-based models, including decision trees, random forests (RFs) and gradient boosted decision trees (GBDTs). Formal robustness ve…
Robust Decision Trees Against Adversarial Examples
Hongge Chen, Huan Zhang, Duane Boning +1
Although adversarial examples and model robustness have been extensively studied in the context of linear models and neural networks, research on this issue in tree-based models an…
The Limitations of Adversarial Training and the Blind-Spot Attack
Huan Zhang, Hongge Chen, Zhao Song +3
The adversarial training procedure proposed by Madry et al. (2018) is one of the most effective methods to defend against adversarial examples in deep neural networks (DNNs). In ou…
Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models
Dong Su, Huan Zhang, Hongge Chen +3
The prediction accuracy has been the long-lasting and sole standard for comparing the performance of different image classification models, including the ImageNet competition. Howe…
Towards Fast Computation of Certified Robustness for ReLU Networks
Tsui-Wei Weng, Huan Zhang, Hongge Chen +5
Verifying the robustness property of a general Rectified Linear Unit (ReLU) network is an NP-complete problem [Katz, Barrett, Dill, Julian and Kochenderfer CAV17]. Although finding…
Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning
Hongge Chen, Huan Zhang, Pin-Yu Chen +2
Visual language grounding is widely studied in modern neural image captioning systems, which typically adopts an encoder-decoder framework consisting of two principal components: a…
Efficient Spatial Variation Characterization via Matrix Completion
Hongge Chen, Duane Boning, Zheng Zhang
In this paper, we propose a novel method to estimate and characterize spatial variations on dies or wafers. This new technique exploits recent developments in matrix completion, en…