b'Tianyu Pang'

research

∙ 07/04/2023

AdAM: Few-Shot Image Generation via Adaptation-Aware Kernel Modulation

Few-shot image generation (FSIG) aims to learn to generate new and diver...

0 Yunqing Zhao, et al. ∙

research

∙ 05/31/2023

Efficient Diffusion Policies for Offline Reinforcement Learning

Offline reinforcement learning (RL) aims to learn optimal policies from ...

0 Bingyi Kang, et al. ∙

research

∙ 05/26/2023

On Evaluating Adversarial Robustness of Large Vision-Language Models

Large vision-language models (VLMs) such as GPT-4 have achieved unpreced...

0 Yunqing Zhao, et al. ∙

research

∙ 05/03/2023

Nonparametric Generative Modeling with Conditional and Locally-Connected Sliced-Wasserstein Flows

Sliced-Wasserstein Flow (SWF) is a promising approach to nonparametric g...

0 Chao Du, et al. ∙

research

∙ 04/13/2023

CoSDA: Continual Source-Free Domain Adaptation

Without access to the source data, source-free domain adaptation (SFDA) ...

0 Haozhe Feng, et al. ∙

research

∙ 03/17/2023

A Recipe for Watermarking Diffusion Models

Recently, diffusion models (DMs) have demonstrated their advantageous po...

0 Yunqing Zhao, et al. ∙

research

∙ 02/21/2023

On Calibrating Diffusion Probabilistic Models

Recently, diffusion probabilistic models (DPMs) have achieved promising ...

0 Tianyu Pang, et al. ∙

research

∙ 02/09/2023

Better Diffusion Models Further Improve Adversarial Training

It has been recognized that the data generated by the denoising diffusio...

0 Zekai Wang, et al. ∙

research

∙ 02/09/2023

Bag of Tricks for Training Data Extraction from Language Models

With the advance of language models, privacy protection is receiving mor...

0 Weichen Yu, et al. ∙

research

∙ 01/28/2023

Does Federated Learning Really Need Backpropagation?

Federated learning (FL) is a general principle for decentralized clients...

0 Haozhe Feng, et al. ∙

research

∙ 05/26/2022

O(N^2) Universal Antisymmetry in Fermionic Neural Networks

Fermionic neural network (FermiNet) is a recently proposed wavefunction ...

0 Tianyu Pang, et al. ∙

research

∙ 03/13/2022

Query-Efficient Black-box Adversarial Attacks Guided by a Transfer-based Prior

Adversarial attacks have been extensively studied in recent years since ...

0 Yinpeng Dong, et al. ∙

research

∙ 03/09/2022

Controllable Evaluation and Generation of Physical Adversarial Patch on Face Recognition

Recent studies have revealed the vulnerability of face recognition model...

0 Xiao Yang, et al. ∙

research

∙ 02/21/2022

Robustness and Accuracy Could Be Reconcilable by (Proper) Definition

The trade-off between robustness and accuracy has been widely studied in...

0 Tianyu Pang, et al. ∙

research

∙ 10/15/2021

Adversarial Attacks on ML Defense Models Competition

Due to the vulnerability of deep neural networks (DNNs) to adversarial e...

0 Yinpeng Dong, et al. ∙

research

∙ 10/13/2021

Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness

The vulnerability of deep neural networks to adversarial examples has mo...

0 Xiao Yang, et al. ∙

research

∙ 07/05/2021

Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks

Transfer-based adversarial attacks can effectively evaluate model robust...

0 Xiao Yang, et al. ∙

research

∙ 06/18/2021

Accumulative Poisoning Attacks on Real-time Data

Collecting training data from untrusted sources exposes machine learning...

0 Tianyu Pang, et al. ∙

research

∙ 06/03/2021

Exploring Memorization in Adversarial Training

It is well known that deep learning models have a propensity for fitting...

0 Yinpeng Dong, et al. ∙

research

∙ 05/31/2021

Adversarial Training with Rectified Rejection

Adversarial training (AT) is one of the most effective strategies for pr...

0 Tianyu Pang, et al. ∙

research

∙ 03/24/2021

Black-box Detection of Backdoor Attacks with Limited Information and Data

Although deep neural networks (DNNs) have made rapid progress in recent ...

0 Yinpeng Dong, et al. ∙

research

∙ 10/01/2020

Bag of Tricks for Adversarial Training

Adversarial training (AT) is one of the most effective strategies for pr...

0 Tianyu Pang, et al. ∙

research

∙ 03/15/2020

Towards Privacy Protection by Generating Adversarial Identity Masks

As billions of personal data such as photos are shared through social me...

5 Xiao Yang, et al. ∙

research

∙ 02/20/2020

Boosting Adversarial Training with Hypersphere Embedding

Adversarial training (AT) is one of the most effective defenses to impro...

13 Tianyu Pang, et al. ∙

research

∙ 02/14/2020

Adversarial Distributional Training for Robust Deep Learning

Adversarial training (AT) is among the most effective techniques to impr...

0 Zhijie Deng, et al. ∙

research

∙ 12/26/2019

Benchmarking Adversarial Robustness

Deep neural networks are vulnerable to adversarial examples, which becom...

0 Yinpeng Dong, et al. ∙

research

∙ 09/25/2019

Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks

It has been widely recognized that adversarial examples can be easily cr...

0 Tianyu Pang, et al. ∙

research

∙ 06/17/2019

Improving Black-box Adversarial Attacks with a Transfer-based Prior

We consider the black-box adversarial setting, where the adversary has t...

0 Shuyu Cheng, et al. ∙

research

∙ 05/25/2019

Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness

Previous work shows that adversarially robust generalization requires la...

0 Tianyu Pang, et al. ∙

research

∙ 04/05/2019

Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks

Deep neural networks are vulnerable to adversarial examples, which can m...

0 Yinpeng Dong, et al. ∙

research

∙ 01/25/2019

Improving Adversarial Robustness via Promoting Ensemble Diversity

Though deep neural networks have achieved significant progress on variou...

0 Tianyu Pang, et al. ∙

research

∙ 03/31/2018

Adversarial Attacks and Defences Competition

To accelerate research on adversarial examples and robustness of machine...

0 Alexey Kurakin, et al. ∙

research

∙ 02/26/2018

Max-Mahalanobis Linear Discriminant Analysis Networks

A deep neural network (DNN) consists of a nonlinear transformation from ...

0 Tianyu Pang, et al. ∙

research

∙ 12/08/2017

Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser

Neural networks are vulnerable to adversarial examples. This phenomenon ...

0 Fangzhou Liao, et al. ∙

research

∙ 10/17/2017

Boosting Adversarial Attacks with Momentum

Deep neural networks are vulnerable to adversarial examples, which poses...

0 Yinpeng Dong, et al. ∙

Tianyu Pang

Featured Co-authors