activity
20192021
most citedRecent Advances in Adversarial Training for Adversarial Robustness

43 citations · 84 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CV20211 cited

Adversarial Purification through Representation Disentanglement

Tao Bai, Jun Zhao, Lanqing Guo +1

Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment. Combined with the idea of advers…

cs.LG202143 cited

Recent Advances in Adversarial Training for Adversarial Robustness

Tao Bai, Jinqi Luo, Jun Zhao +2

Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models. Unlike other defense strategies, adversarial training…

cs.LG20205 cited

Recent Advances in Understanding Adversarial Robustness of Deep Neural Networks

Tao Bai, Jinqi Luo, Jun Zhao

Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based c…

cs.LG20201 cited

Feature Distillation With Guided Adversarial Contrastive Learning

Tao Bai, Jinnan Chen, Jun Zhao +3

Deep learning models are shown to be vulnerable to adversarial examples. Though adversarial training can enhance model robustness, typical approaches are computationally expensive.…

cs.LG2020

AI-GAN: Attack-Inspired Generation of Adversarial Examples

Tao Bai, Jun Zhao, Jinlin Zhu +4

Deep neural networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding imperceptible perturbations to inputs. Recently different attacks and strategies hav…

cs.CR201919 cited

Reviewing and Improving the Gaussian Mechanism for Differential Privacy

Jun Zhao, Teng Wang, Tao Bai +7

Differential privacy provides a rigorous framework to quantify data privacy, and has received considerable interest recently. A randomized mechanism satisfying -differentia…