A Local Perturbation Generation Method for GAN-Generated Face Anti-Forensics

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.

Automated summary

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.