activity
20192022
most citedBlack-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defense

6 citations · 11 across the 5 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2022

Unrestricted Adversarial Samples Based on Non-semantic Feature Clusters Substitution

MingWei Zhou, Xiaobing Pei

Most current methods generate adversarial examples with the norm specification. As a result, many defense methods utilize this property to eliminate the impact of such attack…