Face X-ray for More General Face Forgery Detection

被引:530
|
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
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 50 条
  • [31] Common Forgery Artifact Driven Deepfake Face Detection
    Wu, Haotian
    Wang, Xin
    Wang, Ruobing
    Xiang, Ji
    Ren, Liyue
    PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024, 2024, : 1585 - 1590
  • [32] Face forgery detection with cross-level attention
    Liu, Yaju
    Fei, Jianwei
    Yu, Peipeng
    Yuan, Chengsheng
    Liang, Haopeng
    INTERNATIONAL JOURNAL OF AUTONOMOUS AND ADAPTIVE COMMUNICATIONS SYSTEMS, 2024, 17 (03) : 233 - 246
  • [33] Attentional Local Contrastive Learning for Face Forgery Detection
    Dai, Yunshu
    Fei, Jianwei
    Wang, Huaming
    Xia, Zhihua
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2022, PT I, 2022, 13529 : 709 - 721
  • [34] Exploring Frequency Adversarial Attacks for Face Forgery Detection
    Jia, Shuai
    Ma, Chao
    Yao, Taiping
    Yin, Bangjie
    Ding, Shouhong
    Yang, Xiaokang
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 4093 - 4102
  • [35] Learning dual aggregate features for face forgery detection
    Yuru Kou
    Qian Jiang
    Jun Zhang
    Xin Jin
    Ping Wei
    Shengfa Miao
    Xing Chu
    Neural Computing and Applications, 2025, 37 (4) : 1783 - 1795
  • [36] Exploring Disentangled Content Information for Face Forgery Detection
    Liang, Jiahao
    Shi, Huafeng
    Deng, Weihong
    COMPUTER VISION - ECCV 2022, PT XIV, 2022, 13674 : 128 - 145
  • [37] Generalizing Face Forgery Detection via Uncertainty Learning
    Wu, Yanqi
    Song, Xue
    Chen, Jingjing
    Jiang, Yu-Gang
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 1759 - 1767
  • [38] CORE: Consistent Representation Learning for Face Forgery Detection
    Ni, Yunsheng
    Meng, Depu
    Yu, Changqian
    Quan, Chengbin
    Ren, Dongchun
    Zhao, Youjian
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2022, 2022, : 12 - 21
  • [39] A Dual Domain Attention Mechanism for Face Forgery Detection
    Suo, Yucong
    Zhao, Xiaohan
    Guo, Yuanfang
    Li, Yangxi
    Wang, Yunhong
    2023 IEEE INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS, IJCB, 2023,
  • [40] Learning Local Reconstruction Errors for Face Forgery Detection
    Wu, Haoyu
    Leng, Lingyun
    Yu, Peipeng
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2024, 15 (11) : 1220 - 1227