Face X-ray for More General Face Forgery Detection

被引:609
作者
Li, Lingzhi [1 ,2 ]
Bao, Jianmin [2 ]
Zhang, Ting [2 ]
Yang, Hao [2 ]
Chen, Dong [2 ]
Wen, Fang [2 ]
Guo, Baining [2 ]
机构
[1] Peking Univ, Beijing, Peoples R China
[2] Microsoft Res Asia, Beijing, Peoples R China
来源
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2020年
关键词
IMAGE; LOCALIZATION;
D O I
10.1109/CVPR42600.2020.00505
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper we propose a novel image representation called face X-ray for detecting forgery in face images. The face X-ray of an input face image is a greyscale image that reveals whether the input image can be decomposed into the blending of two images from different sources. It does so by showing the blending boundary for a forged image and the absence of blending for a real image. We observe that most existing face manipulation methods share a common step: blending the altered face into an existing background image. For this reason, face X-ray provides an effective way for detecting forgery generated by most existing face manipulation algorithms. Face X-ray is general in the sense that it only assumes the existence of a blending step and does not rely on any knowledge of the artifacts associated with a specific face manipulation technique. Indeed, the algorithm for computing face X-ray can be trained without fake images generated by any of the state-of-the-art face manipulation methods. Extensive experiments show that face X-ray remains effective when applied to forgery generated by unseen face manipulation techniques, while most existing face forgery detection or deepfake detection algorithms experience a significant performance drop.
引用
收藏
页码:5000 / 5009
页数:10
相关论文
共 48 条
[41]   Detecting Both Machine and Human Created Fake Face Images In the Wild [J].
Tariq, Shahroz ;
Lee, Sangyup ;
Kim, Hoyoung ;
Shin, Youjin ;
Woo, Simon S. .
MPS'18: PROCEEDINGS OF THE 2ND INTERNATIONAL WORKSHOP ON MULTIMEDIA PRIVACY AND SECURITY, 2018, :81-87
[42]   Face2Face: Real-time Face Capture and Reenactment of RGB Videos [J].
Thies, Justus ;
Zollhofer, Michael ;
Stamminger, Marc ;
Theobalt, Christian ;
Niessner, Matthias .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2387-2395
[43]  
Thies Justus, 2019, ARXIV190412356
[44]  
Wang J., 2019, PROC CVPR IEEE, DOI DOI 10.1109/CVPR.2019.00584
[45]  
Wang Run, 2019, ARXIV190906122
[46]   GP-GAN: Towards Realistic High-Resolution Image Blending [J].
Wu, Huikai ;
Zheng, Shuai ;
Zhang, Junge ;
Huang, Kaiqi .
PROCEEDINGS OF THE 27TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA (MM'19), 2019, :2487-2495
[47]   On the Generalization of GAN Image Forensics [J].
Xuan, Xinsheng ;
Peng, Bo ;
Wang, Wei ;
Dong, Jing .
BIOMETRIC RECOGNITION (CCBR 2019), 2019, 11818 :134-141
[48]   Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints [J].
Yu, Ning ;
Davis, Larry ;
Fritz, Mario .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :7555-7565