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
  • [31] Dilated convolution for enhanced extractive summarization: A GAN-based approach with BERT word embedding
    Wu, Huimin
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2024, 46 (02) : 4777 - 4790
  • [32] Robust Localization Method Based on Non-Parametric Probability Density Estimation
    Park, Chee-Hyun
    Chang, Joon-Hyuk
    IEEE ACCESS, 2023, 11 : 61468 - 61480
  • [33] Robust Localization of Signal Source Based on Information Fusion
    Wan, Pengwu
    Yan, Qianli
    Lu, Guangyue
    Wang, Jin
    Huang, Qiongdan
    IEEE SYSTEMS JOURNAL, 2021, 15 (02): : 1764 - 1775
  • [34] Fidora: Robust WiFi-Based Indoor Localization via Unsupervised Domain Adaptation
    Chen, Xi
    Li, Hang
    Zhou, Chenyi
    Liu, Xue
    Wu, Di
    Dudek, Gregory
    IEEE INTERNET OF THINGS JOURNAL, 2022, 9 (12): : 9872 - 9888
  • [35] Reliable Perceptual Loss Computation for GAN-Based Super-Resolution With Edge Texture Metric
    Kim, J.
    Lee, C.
    IEEE ACCESS, 2021, 9 : 120127 - 120137
  • [36] Robust Fingerprint Localization Based on Massive MIMO Systems
    Wang, Xiaojun
    Ren, Yijie
    Sun, Weiguang
    Chen, Xiaoshu
    CHINA COMMUNICATIONS, 2022, 19 (11) : 148 - 159
  • [37] Driver Drowsiness Detection Based on Joint Human Face and Facial Landmark Localization With Cheap Operations
    Wu, Qingtian
    Li, Nannan
    Zhang, Liming
    Yu, Fei Richard
    IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2024, : 19633 - 19645
  • [38] Shape and style GAN-based multispectral data augmentation for crop/weed segmentation in precision farming
    Fawakherji, Mulham
    Suriani, Vincenzo
    Nardi, Daniele
    Bloisi, Domenico Daniele
    CROP PROTECTION, 2024, 184
  • [39] Noise Robust Face Hallucination Based on Smooth Correntropy Representation
    Liu, Licheng
    Feng, Qiying
    Chen, C. L. Philip
    Wang, Yaonan
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (10) : 5953 - 5965
  • [40] ACWGAN: AN AUXILIARY CLASSIFIER WASSERSTEIN GAN-BASED OVERSAMPLING APPROACH FOR MULTI-CLASS IMBALANCED LEARNING
    Liao, Chen
    Dong, Minggang
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2022, 18 (03): : 703 - 721