Towards Universal GAN Image Detection

The ever higher quality and wide diffusion of fake images have spawn a quest for reliable forensic tools. Many GAN image detectors have been proposed, recently. In real world scenarios, however, most of them show limited robustness and generalization ability. Moreover, they often rely on side information not available at test time, that is, they are not universal. We investigate these problems and propose a new GAN image detector based on a limited sub-sampling architecture and a suitable contrastive learning paradigm. Experiments carried out in challenging conditions prove the proposed method to be a first step towards universal GAN image detection, ensuring also good robustness to common image impairments, and good generalization to unseen architectures.

[1]  Giulia Boato,et al.  More Real Than Real: A Study on Human Visual Perception of Synthetic Faces [Applications Corner] , 2021, IEEE Signal Processing Magazine.

[2]  Sophie J. Nightingale,et al.  Synthetic faces: how perceptually convincing are they? , 2021, Journal of Vision.

[3]  Davide Cozzolino,et al.  Are GAN Generated Images Easy to Detect? A Critical Analysis of the State-Of-The-Art , 2021, 2021 IEEE International Conference on Multimedia and Expo (ICME).

[4]  J. Fridrich,et al.  ImageNet Pre-trained CNNs for JPEG Steganalysis , 2020, 2020 IEEE International Workshop on Information Forensics and Security (WIFS).

[5]  David Bau,et al.  What makes fake images detectable? Understanding properties that generalize , 2020, ECCV.

[6]  Ce Liu,et al.  Supervised Contrastive Learning , 2020, NeurIPS.

[7]  Dorothea Kolossa,et al.  Leveraging Frequency Analysis for Deep Fake Image Recognition , 2020, ICML.

[8]  Geoffrey E. Hinton,et al.  A Simple Framework for Contrastive Learning of Visual Representations , 2020, ICML.

[9]  Luisa Verdoliva,et al.  Media Forensics and DeepFakes: An Overview , 2020, IEEE Journal of Selected Topics in Signal Processing.

[10]  Alexei A. Efros,et al.  CNN-Generated Images Are Surprisingly Easy to Spot… for Now , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Tero Karras,et al.  Analyzing and Improving the Image Quality of StyleGAN , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Anil K. Jain,et al.  On the Detection of Digital Face Manipulation , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Luisa Verdoliva,et al.  A Full-Image Full-Resolution End-to-End-Trainable CNN Framework for Image Forgery Detection , 2019, IEEE Access.

[14]  Cristiano Saltori,et al.  Incremental learning for the detection and classification of GAN-generated images , 2019, 2019 IEEE International Workshop on Information Forensics and Security (WIFS).

[15]  Edward Y. Chang,et al.  RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[16]  Xu Zhang,et al.  Detecting and Simulating Artifacts in GAN Fake Images , 2019, 2019 IEEE International Workshop on Information Forensics and Security (WIFS).

[17]  Taesung Park,et al.  Semantic Image Synthesis With Spatially-Adaptive Normalization , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Jing Dong,et al.  On the generalization of GAN image forensics , 2019, CCBR.

[19]  Luisa Verdoliva,et al.  Do GANs Leave Artificial Fingerprints? , 2018, 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR).

[20]  Timo Aila,et al.  A Style-Based Generator Architecture for Generative Adversarial Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Mario Fritz,et al.  Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[22]  Jeff Donahue,et al.  Large Scale GAN Training for High Fidelity Natural Image Synthesis , 2018, ICLR.

[23]  M. Nießner,et al.  ForensicTransfer: Weakly-supervised Domain Adaptation for Forgery Detection , 2018, ArXiv.

[24]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[25]  Jaakko Lehtinen,et al.  Progressive Growing of GANs for Improved Quality, Stability, and Variation , 2017, ICLR.

[26]  Giulia Boato,et al.  RAISE: a raw images dataset for digital image forensics , 2015, MMSys.

[27]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[28]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.