most citedA Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networks

2 citations · 2 across the 2 of their papers we have counts for

collaborators

2 papers

cs.CV2023★ 2 cited

A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networks

Yang Wang, Bo Dong, Ke Xu +4

Deep Neural Networks (DNNs) are widely used for computer vision tasks. However, it has been shown that deep models are vulnerable to adversarial attacks, i.e., their performances d…

cs.CR2022

Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence

Han Fang, Jiyi Zhang, Yupeng Qiu +3

Deep neural networks are vulnerable to adversarial attacks. In this paper, we take the role of investigators who want to trace the attack and identify the source, that is, the part…