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
  • [1] GAN-Based Robust Motion Planning for Mobile Robots Against Localization Attacks
    Tang, Wenbing
    Zhou, Yuan
    Sun, Haiying
    Zhang, Yuhong
    Liu, Yang
    Ding, Zuohua
    Liu, Jing
    He, Jifeng
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (03) : 1603 - 1610
  • [2] Survey on GAN-based face hallucination with its model development
    Liu, Heng
    Zheng, Xiaoyu
    Han, Jungong
    Chu, Yuezhong
    Tao, Tao
    IET IMAGE PROCESSING, 2019, 13 (14) : 2662 - 2672
  • [3] Robust GaN-Based LNAs With Active Epitaxial Current Limiters
    Zhang, Shiyong
    Liu, Li
    Xu, Jianxing
    Wang, Rong
    Zheng, Penghui
    Wang, Hanbin
    Li, Ming
    Kong, Xin
    Tong, Xiaodong
    IEEE MICROWAVE AND WIRELESS COMPONENTS LETTERS, 2021, 31 (12) : 1287 - 1290
  • [4] Using Fully Connected and Convolutional Net for GAN-Based Face Swapping
    Lin, Bo-Shue
    Hsu, Ding-Wen
    Shen, Chin-Han
    Hsiao, Hsu-Feng
    APCCAS 2020: PROCEEDINGS OF THE 2020 IEEE ASIA PACIFIC CONFERENCE ON CIRCUITS AND SYSTEMS (APCCAS 2020), 2020, : 185 - 188
  • [5] A Robust GAN-Generated Face Detection Method Based on Dual-Color Spaces and an Improved Xception
    Chen, Beijing
    Liu, Xin
    Zheng, Yuhui
    Zhao, Guoying
    Shi, Yun-Qing
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (06) : 3527 - 3538
  • [6] Steganographic Secret Sharing With GAN-Based Face Synthesis and Morphing for Trustworthy Authentication in IoT
    Chen, Sisheng
    Chang, Ching-Chun
    Echizen, Isao
    IEEE ACCESS, 2021, 9 : 116427 - 116439
  • [7] GAN-Based Facial Attribute Manipulation
    Liu, Yunfan
    Li, Qi
    Deng, Qiyao
    Sun, Zhenan
    Yang, Ming-Hsuan
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (12) : 14590 - 14610
  • [8] GAN-Based Fusion Adversarial Training
    Cao, Yifan
    Lin, Ying
    Ning, Shengfu
    Pi, Huan
    Zhang, Junyuan
    Hu, Jianpeng
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, KSEM 2022, PT III, 2022, 13370 : 51 - 64
  • [9] Robust Localization Based on Mixed-Norm Minimization Criterion
    Park, Chee-Hyun
    Chang, Joon-Hyuk
    IEEE ACCESS, 2022, 10 : 57080 - 57093
  • [10] Robust Face Super-Resolution via Position Relation Model Based on Global Face Context
    Chen, Liang
    Pan, Jinshan
    Jiang, Junjun
    Zhang, Jiawei
    Wu, Yi
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2020, 29 (9002-9016) : 9002 - 9016