121 citations · 656 across the 45 of their papers we have counts for
9 papers · 1 filter
Benchmarking Adversarial Robustness
Yinpeng Dong, Qi-An Fu, Xiao Yang +4
Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts h…
Interpretable Disentanglement of Neural Networks by Extracting Class-Specific Subnetwork
Yulong Wang, Xiaolin Hu, Hang Su
We propose a novel perspective to understand deep neural networks in an interpretable disentanglement form. For each semantic class, we extract a class-specific functional subnetwo…
Pruning from Scratch
Yulong Wang, Xiaolu Zhang, Lingxi Xie +4
Network pruning is an important research field aiming at reducing computational costs of neural networks. Conventional approaches follow a fixed paradigm which first trains a large…
Improving Black-box Adversarial Attacks with a Transfer-based Prior
Shuyu Cheng, Yinpeng Dong, Tianyu Pang +2
We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous meth…
Boosting Generative Models by Leveraging Cascaded Meta-Models
Fan Bao, Hang Su, Jun Zhu
Deep generative models are effective methods of modeling data. However, it is not easy for a single generative model to faithfully capture the distributions of complex data such as…
Efficient Decision-based Black-box Adversarial Attacks on Face Recognition
Yinpeng Dong, Hang Su, Baoyuan Wu +4
Face recognition has obtained remarkable progress in recent years due to the great improvement of deep convolutional neural networks (CNNs). However, deep CNNs are vulnerable to ad…