期刊
出版社
IEEE
DOI: 10.1109/wacvw50321.2020.9096939
关键词
-
DeepNude, a deep generative software based on image-to-image translation algorithm, excelling in undressing photos of humans and producing realistic nude images. Although the software was later purged from the Internet, image translation algorithms such as CycleGAN, pix2pix, or pix2pixHD can easily be applied by anyone to recreate a new version of DeepNude. This work addresses the issue by introducing a novel aspect of image translating algorithms, namely the possibility of adversarially attacking these algorithms. We modify the input images by the adversarial loss, and thereby the edited images would not be counterfeited easily by these algorithms. The proposed technique can provide a guideline to future research on defending personal images from malicious use of image translation algorithms.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据