A local perturbation generation method for GAN-generated face anti-forensics |
|
Author: | Zhang, Haitao1,2,3; Chen, Beijing1,2,3; Wang, Jinwei1,2,4; |
Organizations: |
1Engineering Research Center of Digital Forensics, Ministry of Education, Nanjing University of Information Science and Technology, Nanjing, China 2School of Computer Science, Nanjing University of Information Science and Technology, Nanjing, China 3Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science and Technology, Nanjing, China
4Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science and Technology, Nanjing, ChinaJiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology (CICAEET), Nanjing University of Information Science and Technology, Nanjing, China
5Center for Machine Vision and Signal Analysis, University of Oulu, Oulu, FI, Finland |
Format: | article |
Version: | accepted version |
Access: | open |
Online Access: | PDF Full Text (PDF, 1.5 MB) |
Persistent link: | http://urn.fi/urn:nbn:fi-fe2023030329564 |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers,
2022
|
Publish Date: | 2023-03-03 |
Description: |
AbstractAlthough 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. see all
|
Series: |
IEEE transactions on circuits and systems for video technology |
ISSN: | 1051-8215 |
ISSN-E: | 1558-2205 |
ISSN-L: | 1051-8215 |
Volume: | 33 |
Issue: | 2 |
Pages: | 661 - 676 |
DOI: | 10.1109/TCSVT.2022.3207310 |
OADOI: | https://oadoi.org/10.1109/TCSVT.2022.3207310 |
Type of Publication: |
A1 Journal article – refereed |
Field of Science: |
113 Computer and information sciences |
Subjects: | |
Funding: |
This work was supported in part by the National Natural Science Foundation of China under Grants 62072251, and 62072250; in part by the Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD) fund. |
Copyright information: |
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |