ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2021, Vol. 58 ›› Issue (7): 1476-1489.doi: 10.7544/issn1000-1239.2021.20200803

所属专题: 2021虚假信息检测专题

• 信息处理 • 上一篇    下一篇

基于域对抗学习的可泛化虚假人脸检测方法研究

翁泽佳,陈静静,姜育刚   

  1. (复旦大学计算机科学技术学院 上海 201203) (上海市智能信息处理重点实验室(复旦大学计算机科学技术学院) 上海 200433) (zjweng20@fudan.edu.cn)
  • 出版日期: 2021-07-01
  • 基金资助: 
    国家自然科学基金项目(62032006)

On the Generalization of Face Forgery Detection with Domain Adversarial Learning

Weng Zejia, Chen Jingjing, Jiang Yugang   

  1. (School of Computer Science, Fudan University, Shanghai 201203) (Shanghai Key Laboratory of Intelligent Information Processing (School of Computer Science, Fudan University), Shanghai 200433)
  • Online: 2021-07-01
  • Supported by: 
    This work was supported by the National Natural Science Foundation of China (62032006).

摘要: 随着生成式对抗网络(generative adversarial networks, GAN)的快速发展,虚假人脸生成技术取得了显著进展.为了降低以假乱真的人脸生成技术给社会带来的危害,虚假人脸鉴别成为一个非常重要的课题,吸引了国内外研究者的广泛关注.然而,目前虚假人脸鉴别的研究工作相对较少,仍然有许多问题需要被解决.其中如何提升鉴别模型的迁移泛化能力是至关重要的问题,也是虚假人脸检测任务能否实际投入使用的关键所在.如何提升虚假人脸鉴别方法的泛化能力,即做到在没有见过的生成方法产生的数据上仍然准确有效非常重要.对此,提出了基于域对抗学习的可泛化虚假人脸检测模型,通过引入领域对抗分支,弱化特征提取器对于特定生成模型非鲁棒性特征的提取,模型能够抽取鲁棒性更强、泛化能力更高的特征,从而在没有见过的生成方法产生的虚假人脸图片上具有更好的鉴别表现.实验结果表明:所提出的方法能够提升鉴别模型的泛化能力,显著提升虚假人脸鉴别模型在未知生成模型产生的虚假图像上的性能.

关键词: 虚假人脸检测, 域自适应, 域对抗学习, 鲁棒特征学习, 泛化性

Abstract: With the rapid development of generative adversarial networks (GAN), breakthrough progress has been made in fake face generation. In order to reduce the harmful effects of fake face generation technology to society, fake face identification has become a very important topic, which has attracted numerous research efforts. Although impressive progress has been made in fake face identification, there are still many problems to be solved. Among them, how to improve the generalization ability of the fake face detection model is a crucial issue, and it is also the key to deploy fake face detection techniques in real-world scenarios. This paper studies the fake face identification problem, aiming to improve the generalization ability of the fake face identification model. Motivated by the idea of unsupervised domain adaptation, this paper introduces the domain adversarial branch to weaken the extraction of non-robust features of specific generative models by the feature extractor, so that the model can extract features with stronger robustness and higher generalization ability, improving the identification performance on the fake face images generated by unknown GANs. Experimental results show that the method proposed in this paper can effectively improve the generalization ability of the identification model, and significantly improve the performance of the fake face identification model on the fake images generated by the unknown generation model.

Key words: face forgery detection, domain adaptation, domain adversarial learning, robust feature learning, generalization

中图分类号: