Back to articles
Volume: 33 | Article ID: art00007
Detection, Attribution and Localization of GAN Generated Images
  DOI :  10.2352/ISSN.2470-1173.2021.4.MWSF-276  Published OnlineJanuary 2021

Recent advances in Generative Adversarial Networks (GANs) have led to the creation of realistic-looking digital images that pose a major challenge to their detection by humans or computers. GANs are used in a wide range of tasks, from modifying small attributes of an image (StarGAN [14]), transferring attributes between image pairs (CycleGAN [92]), as well as generating entirely new images (ProGAN [37], StyleGAN [38], SPADE/GauGAN [65]). In this paper, we propose a novel approach to detect, attribute and localize GAN generated images that combines image features with deep learning methods. For every image, co-occurrence matrices are computed on neighborhood pixels of RGB channels in different directions (horizontal, vertical and diagonal). A deep learning network is then trained on these features to detect, attribute and localize these GAN generated/manipulated images. A large scale evaluation of our approach on 5 GAN datasets comprising over 2.76 million images (ProGAN, StarGAN, CycleGAN, StyleGAN and SPADE/GauGAN) shows promising results in detecting GAN generated images.

Subject Areas :
Views 119
Downloads 9
 articleview.views 119
 articleview.downloads 9
  Cite this article 

Michael Goebel, Lakshmanan Nataraj, Tejaswi Nanjundaswamy, Tajuddin Manhar Mohammed, Shivkumar Chandrasekaran, B. S. Manjunath, "Detection, Attribution and Localization of GAN Generated Imagesin Proc. IS&T Int’l. Symp. on Electronic Imaging: Media Watermarking, Security, and Forensics,  2021,  pp 276-1 - 276-11,

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2021
Electronic Imaging
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA