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
  • [21] A GAN-Based Anomaly Detection Approach for Imbalanced Industrial Time Series
    Jiang, Wenqian
    Hong, Yang
    Zhou, Beitong
    He, Xin
    Cheng, Cheng
    IEEE ACCESS, 2019, 7 : 143608 - 143619
  • [22] M2H-GAN: A GAN-based Mapping from Machine to Human Transcripts for Speech Understanding
    Parcollet, Titouan
    Morchid, Mohamed
    Bost, Xavier
    Linares, Georges
    INTERSPEECH 2019, 2019, : 804 - 808
  • [23] A GAN-based anomaly detector using multi-feature fusion and selection
    Dai, Huafeng
    Wang, Jyunrong
    Zhong, Quan
    Chen, Taogen
    Liu, Hao
    Zhang, Xuegang
    Lu, Rongsheng
    SCIENTIFIC REPORTS, 2024, 14 (01)
  • [24] GAN-based disentanglement learning for chest X-ray rib suppression
    Han, Luyi
    Lyu, Yuanyuan
    Peng, Cheng
    Zhou, S. Kevin
    MEDICAL IMAGE ANALYSIS, 2022, 77
  • [25] DGTAD: decomposition GAN-based transformer for anomaly detection in multivariate time series data
    Chen, Zixin
    Yu, Jiong
    Tan, Qiyin
    Li, Shu
    Du, XuSheng
    APPLIED INTELLIGENCE, 2024, 54 (24) : 13038 - 13056
  • [26] A Novel System for Recovery Time Measurements of GaN-Based Low-Noise Amplifiers
    Tomaz, Antonio
    Gerlich, Stefan
    Rudolph, Matthias
    Andrei, Cristina
    PROCEEDINGS OF THE 2022 14TH GERMAN MICROWAVE CONFERENCE (GEMIC), 2022, : 65 - 68
  • [27] GAN-Based Multi-Task Learning Approach for Prognostics and Health Management of IIoT
    Behera, Sourajit
    Misra, Rajiv
    Sillitti, Alberto
    IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2024, 21 (03) : 2742 - 2762
  • [28] Robust Inertial-Aided Underwater Localization Based on Imaging Sonar Keyframes
    Xu, Yang
    Zheng, Ronghao
    Zhang, Senlin
    Liu, Meiqin
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
  • [29] Multi-attention-based approach for deepfake face and expression swap detection and localization
    Saima Waseem
    Syed Abdul Rahman Syed Abu-Bakar
    Zaid Omar
    Bilal Ashfaq Ahmed
    Saba Baloch
    Adel Hafeezallah
    EURASIP Journal on Image and Video Processing, 2023
  • [30] Multi-attention-based approach for deepfake face and expression swap detection and localization
    Waseem, Saima
    Abu-Bakar, Syed Abdul Rahman Syed
    Omar, Zaid
    Ahmed, Bilal Ashfaq
    Baloch, Saba
    Hafeezallah, Adel
    EURASIP JOURNAL ON IMAGE AND VIDEO PROCESSING, 2023, 2023 (01)