Exploring adversarial fake images on face manifold | |
Li Dongze1,2; Wang Wei2![]() ![]() | |
2021 | |
会议名称 | 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
会议日期 | 20-25 June 2021 |
会议地点 | Nashville, TN, USA |
摘要 | Images synthesized by powerful generative adversarial network (GAN) based methods have drawn moral and privacy concerns. Although image forensic models have reached great performance in detecting fake images from real ones, these models can be easily fooled with a simple adversarial attack. But, the noise adding adversarial samples are also arousing suspicion. In this paper, instead of adding adversarial noise, we optimally search adversarial points on face manifold to generate anti-forensic fake face images. We iteratively do a gradient-descent with each small step in the latent space of a generative model, e.g. Style-GAN, to find an adversarial latent vector, which is similar to norm-based adversarial attack but in latent space. Then, the generated fake images driven by the adversarial latent vectors with the help of GANs can defeat main-stream forensic models. For examples, they make the accuracy of deepfake detection models based on Xception or EfficientNet drop from over 90% to nearly 0%, mean-while maintaining high visual quality. In addition, we find manipulating noise vectors n at different levels have different impacts on attack success rate, and the generated adversarial images mainly have changes on facial texture or face attributes. |
DOI | 10.1109/CVPR46437.2021.00573 |
收录类别 | EI |
语种 | 英语 |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 多模态智能 |
国重实验室规划方向分类 | 多模态协同认知 |
是否有论文关联数据集需要存交 | 否 |
引用统计 | |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/51540 |
专题 | 模式识别实验室 |
通讯作者 | Wang Wei |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences 2.Center for Research on Intelligent Perception and Computing, CASIA |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Li Dongze,Wang Wei,Fan Hongxing,et al. Exploring adversarial fake images on face manifold[C],2021. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Exploring_Adversaria(4424KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论