FakeLocator: Robust Localization of GAN-Based Face Manipulations

被引:34
作者
Huang, Yihao [1 ]
Juefei-Xu, Felix [2 ]
Guo, Qing [3 ]
Liu, Yang [3 ,4 ]
Pu, Geguang [1 ,5 ]
机构
[1] East China Normal Univ, Sch Software Engn, Shanghai 200050, Peoples R China
[2] Alibaba Grp, Sunnyvale, CA 94085 USA
[3] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore 639798, Singapore
[4] Zhejiang Sci Tech Univ, Sch Comp Sci & Technol, Hangzhou 314423, Peoples R China
[5] Shanghai Ind Control Safety Innovat Technol Co Lt, Shanghai 200331, Peoples R China
基金
新加坡国家研究基金会;
关键词
Faces; Location awareness; Videos; Information integrity; Robustness; Forensics; Image resolution; DeepFake; face manipulation; DeepFake detection and localization; NETWORKS;
D O I
10.1109/TIFS.2022.3141262
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Full face synthesis and partial face manipulation by virtue of the generative adversarial networks (GANs) and its variants have raised wide public concerns. In the multi-media forensics area, detecting and ultimately locating the image forgery has become an imperative task. In this work, we investigate the architecture of existing GAN-based face manipulation methods and observe that the imperfection of upsampling methods therewithin could be served as an important asset for GAN-synthesized fake image detection and forgery localization. Based on this basic observation, we have proposed a novel approach, termed FakeLocator, to obtain high localization accuracy, at full resolution, on manipulated facial images. To the best of our knowledge, this is the very first attempt to solve the GAN-based fake localization problem with a gray-scale fakeness map that preserves more information of fake regions. To improve the universality of FakeLocator across multifarious facial attributes, we introduce an attention mechanism to guide the training of the model. To improve the universality of FakeLocator across different DeepFake methods, we propose partial data augmentation and single sample clustering on the training images. Experimental results on popular FaceForensics++, DFFD datasets and seven different state-of-the-art GAN-based face generation methods have shown the effectiveness of our method. Compared with the baselines, our method performs better on various metrics. Moreover, the proposed method is robust against various real-world facial image degradations such as JPEG compression, low-resolution, noise, and blur.
引用
收藏
页码:2657 / 2672
页数:16
相关论文
共 50 条
  • [41] A robust compressed sensing image encryption algorithm based on GAN and CNN
    Chai, Xiuli
    Tian, Ye
    Gan, Zhihua
    Lu, Yang
    Wu, Xiang-Jun
    Long, Guoqiang
    JOURNAL OF MODERN OPTICS, 2022, 69 (02) : 103 - 120
  • [42] An Indoor Robust Localization Algorithm Based on Data Association Technique
    Cheng, Long
    Wang, Yong
    Xue, Mingkun
    Bi, Yangyang
    SENSORS, 2020, 20 (22) : 1 - 18
  • [43] A novel Alzheimer?s disease detection approach using GAN-based brain slice image enhancement
    Zhang, Lin
    Ren, Lei
    Bai, Tian
    Du, Mingyu
    Ruan, Li
    Yang, Yuan
    Qian, Guanghao
    Meng, Zihao
    Zhao, Li
    Deen, M. Jamal
    NEUROCOMPUTING, 2022, 492 : 353 - 369
  • [44] A singular value decomposition representation based approach for robust face recognition
    Long, Xianzhong
    Zhang, Zhiyi
    Li, Yun
    MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81 (06) : 8283 - 8308
  • [45] A singular value decomposition representation based approach for robust face recognition
    Xianzhong Long
    Zhiyi Zhang
    Yun Li
    Multimedia Tools and Applications, 2022, 81 : 8283 - 8308
  • [46] ROBUST SUPER-RESOLUTION GAN, WITH MANIFOLD-BASED AND PERCEPTION LOSS
    Upadhyay, Uddeshya
    Awate, Suyash P.
    2019 IEEE 16TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI 2019), 2019, : 1372 - 1376
  • [47] Impact of GAN-based lesion-focused medical image super-resolution on the robustness of radiomic features
    de Farias, Erick Costa
    di Noia, Christian
    Han, Changhee
    Sala, Evis
    Castelli, Mauro
    Rundo, Leonardo
    SCIENTIFIC REPORTS, 2021, 11 (01)
  • [48] An 18-31-GHz GaN-Based LNA With 0.8-dB Minimum NF and High Robustness
    Zhang, Shiyong
    Xu, Jianxing
    Zheng, Penghui
    Wang, Rong
    Tong, Xiaodong
    IEEE MICROWAVE AND WIRELESS COMPONENTS LETTERS, 2020, 30 (09) : 896 - 899
  • [49] MPF: A Robust Vehicle Localization Framework Based on Topological Map and Odometry
    Zhang, Zhike
    Wang, Tianle
    Gu, Shuxia
    Xiang, Zhiyu
    IEEE SENSORS JOURNAL, 2023, 23 (07) : 7242 - 7252
  • [50] Towards Robust VLC Beacon Identification in Camera Based Localization Systems
    Ratosi, Mark
    Simon, Gyula
    2019 INTERNATIONAL CONFERENCE ON INDOOR POSITIONING AND INDOOR NAVIGATION (IPIN), 2019,