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
[21]   Learning to Detect Fake Face Images in the Wild [J].
Hsu, Chih-Chung ;
Lee, Chia-Yen ;
Zhuang, Yi-Xiu .
2018 INTERNATIONAL SYMPOSIUM ON COMPUTER, CONSUMER AND CONTROL (IS3C 2018), 2018, :388-391
[22]  
Khodabakhsh A, 2018, 2018 INTERNATIONAL CONFERENCE OF THE BIOMETRICS SPECIAL INTEREST GROUP (BIOSIG)
[23]  
King DB, 2015, ACS SYM SER, V1214, P1
[24]  
Li Y., 2019, ARXIV190912962
[25]   Do GANs Leave Artificial Fingerprints? [J].
Marra, Francesco ;
Gragnaniello, Diego ;
Verdoliva, Luisa ;
Poggi, Giovanni .
2019 2ND IEEE CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2019), 2019, :506-511
[26]   Detection of GAN-generated Fake Images over Social Networks [J].
Marra, Francesco ;
Gragnaniello, Diego ;
Cozzolino, Davide ;
Verdoliva, Luisa .
IEEE 1ST CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2018), 2018, :384-389
[27]  
Marra Francesco, 2019, ARXIV191001568
[28]   Fake Faces Identification via Convolutional Neural Network [J].
Mo, Huaxiao ;
Chen, Bolin ;
Luo, Weiqi .
PROCEEDINGS OF THE 6TH ACM WORKSHOP ON INFORMATION HIDING AND MULTIMEDIA SECURITY (IH&MMSEC'18), 2018, :43-47
[29]  
Nguyen Huy H, 2019, P 2019 5 INT WORKSH, DOI DOI 10.1145/3366623.3368133
[30]   k☆NNCA: A Location Privacy Preserving Method for Semi-honest Mobile Users [J].
Pan, Xiao ;
Wu, Lei ;
Piao, Chunhui .
2012 NINTH IEEE INTERNATIONAL CONFERENCE ON E-BUSINESS ENGINEERING (ICEBE), 2012, :17-24