activity
20172023
most citedImproving Adversarial Robustness via Promoting Ensemble Diversity

190 citations · 244 across the 9 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2020

Boosting Adversarial Training with Hypersphere Embedding

Tianyu Pang, Xiao Yang, Yinpeng Dong +3

Adversarial training (AT) is one of the most effective defenses against adversarial attacks for deep learning models. In this work, we advocate incorporating the hypersphere embedd…

cs.LG2019

Triple Generative Adversarial Networks

Chongxuan Li, Kun Xu, Jiashuo Liu +2

We propose a unified game-theoretical framework to perform classification and conditional image generation given limited supervision. It is formulated as a three-player minimax gam…

cs.LG2019

Efficient Global String Kernel with Random Features: Beyond Counting Substructures

Lingfei Wu, Ian En-Hsu Yen, Siyu Huo +5

Analysis of large-scale sequential data has been one of the most crucial tasks in areas such as bioinformatics, text, and audio mining. Existing string kernels, however, either (i)…

cs.LG2019

Understanding and Stabilizing GANs' Training Dynamics with Control Theory

Kun Xu, Chongxuan Li, Jun Zhu +1

Generative adversarial networks (GANs) are effective in generating realistic images but the training is often unstable. There are existing efforts that model the training dynamics…

cs.LG2019

Mixup Inference: Better Exploiting Mixup to Defend Adversarial Attacks

Tianyu Pang, Kun Xu, Jun Zhu

It has been widely recognized that adversarial examples can be easily crafted to fool deep networks, which mainly root from the locally non-linear behavior nearby input examples. A…

cs.LG20196 cited

Multi-objects Generation with Amortized Structural Regularization

Kun Xu, Chongxuan Li, Jun Zhu +1

Deep generative models (DGMs) have shown promise in image generation. However, most of the existing work learn the model by simply optimizing a divergence between the marginal dist…