50 citations · 112 across the 27 of their papers we have counts for
Showing 2019Show all
3 papers · 1 filter
cs.CR2019★ 2 cited
A New Ensemble Method for Concessively Targeted Multi-model Attack
Ziwen He, Wei Wang, Xinsheng Xuan +2
It is well known that deep learning models are vulnerable to adversarial examples crafted by maliciously adding perturbations to original inputs. There are two types of attacks: ta…
cs.CV2019★ 2 cited
Scalable Fine-grained Generated Image Classification Based on Deep Metric Learning
Xinsheng Xuan, Bo Peng, Wei Wang +1
Recently, generated images could reach very high quality, even human eyes could not tell them apart from real images. Although there are already some methods for detecting generate…
cs.CV2019★ 10 cited
On the generalization of GAN image forensics
Xinsheng Xuan, Bo Peng, Wei Wang +1
Recently the GAN generated face images are more and more realistic with high-quality, even hard for human eyes to detect. On the other hand, the forensics community keeps on develo…