期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
卷 33, 期 2, 页码 661-676出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSVT.2022.3207310
关键词
Faces; Detectors; Perturbation methods; Forensics; Visualization; Face recognition; Generative adversarial networks; Local perturbation; generated face; anti-forensics; generative adversarial network; double mask
In this paper, an effective local perturbation generation method is proposed to expose the vulnerability of state-of-the-art forensic detectors for GAN-generated faces. The method mines the common areas of concern in multiple detectors' decision-making and generates local anti-forensic perturbations using GANs to enhance the visual quality and transferability of anti-forensic faces. Experimental results demonstrate the method's advantage over the state-of-the-art methods in terms of anti-forensic success rate, imperceptibility, and transferability.
Although the current generative adversarial networks (GAN)-generated face forensic detectors based on deep neural networks (DNNs) have achieved considerable performance, they are vulnerable to adversarial attacks. In this paper, an effective local perturbation generation method is proposed to expose the vulnerability of state-of-the-art forensic detectors. The main idea is to mine the fake faces' areas of common concern in multiple-detectors' decision-making, then generate local anti-forensic perturbations by GANs in these areas to enhance the visual quality and transferability of anti-forensic faces. Meanwhile, in order to improve the anti-forensic effect, a double- mask (soft mask and hard mask) strategy and a three-part loss (the GAN training loss, the adversarial loss consisting of ensemble classification loss and ensemble feature loss, and the regularization loss) are designed for the training of the generator. Experiments conducted on fake faces generated by StyleGAN demonstrate the proposed method's advantage over the state-of-the-art methods in terms of anti-forensic success rate, imperceptibility, and transferability. The source code is available at https://github.com/imagecbj/A-Local-Perturbation-Generation-Method-for-GAN-generated-Face-Anti-forensics.
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