most citedBoosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation

22 citations · 49 across the 11 of their papers we have counts for

collaborators

12 papers

cs.LG20229 cited

Stability Analysis and Generalization Bounds of Adversarial Training

Jiancong Xiao, Yanbo Fan, Ruoyu Sun +2

In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set. This phenomenon…

cs.CV202222 cited

Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation

Zeyu Qin, Yanbo Fan, Yi Liu +4

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work…

cs.LG20223 cited

Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis

Jiancong Xiao, Zeyu Qin, Yanbo Fan +3

Adversarial Training (AT) has been demonstrated as one of the most effective methods against adversarial examples. While most existing works focus on AT with a single type of pertu…

cs.LG20223 cited

Understanding Adversarial Robustness Against On-manifold Adversarial Examples

Jiancong Xiao, Liusha Yang, Yanbo Fan +2

Deep neural networks (DNNs) are shown to be vulnerable to adversarial examples. A well-trained model can be easily attacked by adding small perturbations to the original data. One…

cs.CV2022

Improving the Latent Space of Image Style Transfer

Yunpeng Bai, Cairong Wang, Chun Yuan +2

Existing neural style transfer researches have studied to match statistical information between the deep features of content and style images, which were extracted by a pre-trained…

cs.CV2022

Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attacks

Xu Han, Anmin Liu, Yifeng Xiong +2

Deep neural networks have shown to be very vulnerable to adversarial examples crafted by adding human-imperceptible perturbations to benign inputs. After achieving impressive attac…