b'Huan Zhang'

research

∙ 09/05/2023

Symbolic Music Representations for Classification Tasks: A Systematic Evaluation

Music Information Retrieval (MIR) has seen a recent surge in deep learni...

0 Huan Zhang, et al. ∙

research

∙ 08/28/2023

DiffSmooth: Certifiably Robust Learning via Diffusion Models and Local Smoothing

Diffusion models have been leveraged to perform adversarial purification...

0 Jiawei Zhang, et al. ∙

research

∙ 08/19/2023

Robust Mixture-of-Expert Training for Convolutional Neural Networks

Sparsely-gated Mixture of Expert (MoE), an emerging deep model architect...

0 Yihua Zhang, et al. ∙

research

∙ 04/26/2023

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

In this paper, we define, evaluate, and improve the “relay-generalizatio...

0 Li-Cheng Lan, et al. ∙

research

∙ 03/29/2023

Queer In AI: A Case Study in Community-Led Participatory AI

We present Queer in AI as a case study for community-led participatory d...

5 Organizers Of Queer in AI, et al. ∙

research

∙ 02/02/2023

Provably Bounding Neural Network Preimages

Most work on the formal verification of neural networks has focused on b...

0 Suhas Kotha, et al. ∙

research

∙ 11/07/2022

Are AlphaZero-like Agents Robust to Adversarial Perturbations?

The success of AlphaZero (AZ) has demonstrated that neural-network-based...

1 Li-Cheng Lan, et al. ∙

research

∙ 10/30/2022

FI-ODE: Certified and Robust Forward Invariance in Neural ODEs

We study how to certifiably enforce forward invariance properties in neu...

6 Yujia Huang, et al. ∙

research

∙ 10/13/2022

Efficiently Computing Local Lipschitz Constants of Neural Networks via Bound Propagation

Lipschitz constants are connected to many properties of neural networks,...

0 Zhouxing Shi, et al. ∙

research

∙ 09/24/2022

Outage Performance Analysis of Type-I HARQ Aided V2V Communications

Vehicle-to-vehicle (V2V) communications under dense urban environments u...

0 Huan Zhang, et al. ∙

research

∙ 09/23/2022

Outage Performance Analysis of HARQ-Aided Multi-RIS Systems

Reconfigurable intelligent surface (RIS) has recently attracted a spurt ...

0 Qi Cao, et al. ∙

research

∙ 09/23/2022

Outage Performance Analysis of Full-Correlated Rayleigh MIMO Channels

The outage performance of multiple-input multiple-output (MIMO) techniqu...

0 Huan Zhang, et al. ∙

research

∙ 09/23/2022

On the Performance of Variable-Rate HARQ-IR over Beckmann Fading Channels

This paper thoroughly investigates the performance of variable-rate hybr...

0 Zheng Shi, et al. ∙

research

∙ 09/23/2022

Performance Analysis of MIMO-HARQ Assisted V2V Communications With Keyhole Effect

Vehicle-to-vehicle (V2V) communications under dense urban environments u...

0 Huan Zhang, et al. ∙

research

∙ 08/11/2022

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

Bound propagation methods, when combined with branch and bound, are amon...

7 Huan Zhang, et al. ∙

research

∙ 06/15/2022

Linearity Grafting: Relaxed Neuron Pruning Helps Certifiable Robustness

Certifiable robustness is a highly desirable property for adopting deep ...

4 Tianlong Chen, et al. ∙

research

∙ 05/29/2022

On the Robustness of Safe Reinforcement Learning under Observational Perturbations

Safe reinforcement learning (RL) trains a policy to maximize the task re...

0 Zuxin Liu, et al. ∙

research

∙ 05/14/2022

BronchusNet: Region and Structure Prior Embedded Representation Learning for Bronchus Segmentation and Classification

CT-based bronchial tree analysis plays an important role in the computer...

0 Wenhao Huang, et al. ∙

research

∙ 12/22/2021

Sum-Rate Maximization of RIS-Aided Multi-User MIMO Systems With Statistical CSI

This paper investigates a reconfigurable intelligent surface (RIS)-aided...

0 Huan Zhang, et al. ∙

research

∙ 12/15/2021

Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks

Recently, video-based action recognition methods using convolutional neu...

0 Jaehui Hwang, et al. ∙

research

∙ 11/02/2021

Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds

Certified robustness is a desirable property for deep neural networks in...

10 Yujia Huang, et al. ∙

research

∙ 10/18/2021

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

Due to the proliferation of renewable energy and its intrinsic intermitt...

0 Alexander Pan, et al. ∙

research

∙ 04/30/2021

Deep Image Destruction: A Comprehensive Study on Vulnerability of Deep Image-to-Image Models against Adversarial Attacks

Recently, the vulnerability of deep image classification models to adver...

0 Jun-Ho Choi, et al. ∙

research

∙ 04/12/2021

Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation

Robustness and counterfactual bias are usually evaluated on a test datas...

5 Chong Zhang, et al. ∙

research

∙ 03/31/2021

Fast Certified Robust Training via Better Initialization and Shorter Warmup

Recently, bound propagation based certified adversarial defense have bee...

0 Zhouxing Shi, et al. ∙

research

∙ 03/11/2021

Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Verification

Recent works in neural network verification show that cheap incomplete v...

0 Shiqi Wang, et al. ∙

research

∙ 02/16/2021

Does deep machine vision have just noticeable difference (JND)?

As an important perceptual characteristic of the Human Visual System (HV...

12 Jian Jin, et al. ∙

research

∙ 01/21/2021

Robust Reinforcement Learning on State Observations with Learned Optimal Adversary

We study the robustness of reinforcement learning (RL) with adversariall...

0 Huan Zhang, et al. ∙

research

∙ 11/27/2020

Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers

Formal verification of neural networks (NNs) is a challenging and import...

0 Kaidi Xu, et al. ∙

research

∙ 10/22/2020

An Efficient Adversarial Attack for Tree Ensembles

We study the problem of efficient adversarial attacks on tree based ense...

0 Chong Zhang, et al. ∙

research

∙ 10/15/2020

Automatic Analysis and Influence of Hierarchical Structure on Melody, Rhythm and Harmony in Popular Music

Repetition is a basic indicator of musical structure. This study introdu...

0 Shuqi Dai, et al. ∙

research

∙ 08/20/2020

On ℓ_p-norm Robustness of Ensemble Stumps and Trees

Recent papers have demonstrated that ensemble stumps and trees could be ...

0 Yihan Wang, et al. ∙

research

∙ 06/15/2020

The Limit of the Batch Size

Large-batch training is an efficient approach for current distributed de...

22 Yang You, et al. ∙

research

∙ 05/11/2020

Spanning Attack: Reinforce Black-box Attacks with Unlabeled Data

Adversarial black-box attacks aim to craft adversarial perturbations by ...

0 Lu Wang, et al. ∙

research

∙ 04/07/2020

Towards Non-task-specific Distillation of BERT via Sentence Representation Approximation

Recently, BERT has become an essential ingredient of various NLP deep mo...

0 Bowen Wu, et al. ∙

research

∙ 03/19/2020

Robust Deep Reinforcement Learning against Adversarial Perturbations on Observations

Deep Reinforcement Learning (DRL) is vulnerable to small adversarial per...

0 Huan Zhang, et al. ∙

research

∙ 02/28/2020

Automatic Perturbation Analysis on General Computational Graphs

Linear relaxation based perturbation analysis for neural networks, which...

11 Kaidi Xu, et al. ∙

research

∙ 02/16/2020

Robustness Verification for Transformers

Robustness verification that aims to formally certify the prediction beh...

9 Zhouxing Shi, et al. ∙

research

∙ 01/08/2020

MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius

Adversarial training is one of the most popular ways to learn robust mod...

4 Runtian Zhai, et al. ∙

research

∙ 12/20/2019

MFPN: A Novel Mixture Feature Pyramid Network of Multiple Architectures for Object Detection

Feature pyramids are widely exploited in many detectors to solve the sca...

12 Tingting Liang, et al. ∙

research

∙ 11/20/2019

Robust Triple-Matrix-Recovery-Based Auto-Weighted Label Propagation for Classification

The graph-based semi-supervised label propagation algorithm has delivere...

20 Huan Zhang, et al. ∙

research

∙ 11/08/2019

Reducing Sentiment Bias in Language Models via Counterfactual Evaluation

Recent improvements in large-scale language models have driven progress ...

0 Po-Sen Huang, et al. ∙

research

∙ 10/31/2019

Enhancing Certifiable Robustness via a Deep Model Ensemble

We propose an algorithm to enhance certified robustness of a deep model ...

0 Huan Zhang, et al. ∙

research

∙ 08/14/2019

MemeFaceGenerator: Adversarial Synthesis of Chinese Meme-face from Natural Sentences

Chinese meme-face is a special kind of internet subculture widely spread...

0 Yifu Chen, et al. ∙

research

∙ 06/16/2019

Defending Against Adversarial Attacks Using Random Forests

As deep neural networks (DNNs) have become increasingly important and po...

1 Yifan Ding, et al. ∙

research

∙ 06/14/2019

Towards Stable and Efficient Training of Verifiably Robust Neural Networks

Training neural networks with verifiable robustness guarantees is challe...

0 Huan Zhang, et al. ∙

research

∙ 06/10/2019

Robustness Verification of Tree-based Models

We study the robustness verification problem for tree-based models, incl...

0 Hongge Chen, et al. ∙

research

∙ 06/09/2019

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

Recent works have shown the effectiveness of randomized smoothing as a s...

4 Hadi Salman, et al. ∙

research

∙ 04/15/2019

Asymptotic Outage Analysis of Spatially Correlated Rayleigh MIMO Channels

The outage performance of multiple-input multiple-output (MIMO) techniqu...

0 Zheng Shi, et al. ∙

research

∙ 04/12/2019

Evaluating Robustness of Deep Image Super-Resolution against Adversarial Attacks

Single-image super-resolution aims to generate a high-resolution version...

0 Jun-Ho Choi, et al. ∙

Huan Zhang

Featured Co-authors