Detection, Attribution and Localization of GAN Generated Images

Abstract

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 [91]), as well as generating entirely new images (ProGAN [36], StyleGAN [37], SPADE/GauGAN [64]). 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.

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Learning to Discover Cross-Domain Relations with Generative Adversarial Networks
• Invertible Conditional GANs for image editing
• Unsupervised Cross-Domain Image Generation
• Identification of Deep Network Generated Images Using Disparities in Color Components
• Leveraging Frequency Analysis for Deep Fake Image Recognition
• Learning Rich Features for Image Manipulation Detection
• Detecting GAN-generated Imagery using Color Cues
• GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection
• TequilaGAN: How to easily identify GAN samples
• One-Shot GAN Generated Fake Face Detection

Cited by in corpus (3)

• Robust Attentive Deep Neural Network for Exposing GAN-generated Faces
• Seam Carving Detection and Localization using Two-Stage Deep Neural Networks
• Holistic Image Manipulation Detection using Pixel Co-occurrence Matrices