Detecting GAN generated Fake Images using Co-occurrence Matrices

Abstract

The advent of Generative Adversarial Networks (GANs) has brought about completely novel ways of transforming and manipulating pixels in digital images. GAN based techniques such as Image-to-Image translations, DeepFakes, and other automated methods have become increasingly popular in creating fake images. In this paper, we propose a novel approach to detect GAN generated fake images using a combination of co-occurrence matrices and deep learning. We extract co-occurrence matrices on three color channels in the pixel domain and train a model using a deep convolutional neural network (CNN) framework. Experimental results on two diverse and challenging GAN datasets comprising more than 56,000 images based on unpaired image-to-image translations (cycleGAN [1]) and facial attributes/expressions (StarGAN [2]) show that our approach is promising and achieves more than 99% classification accuracy in both datasets. Further, our approach also generalizes well and achieves good results when trained on one dataset and tested on the other.

References in corpus (11)

• 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
• Learning Rich Features for Image Manipulation Detection
• Detecting GAN-generated Imagery using Color Cues
• TequilaGAN: How to easily identify GAN samples
• Do GANs leave artificial fingerprints?

Cited by in corpus (12)

• GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis
• Detecting and Simulating Artifacts in GAN Fake Images
• FakeSpotter: A Simple yet Robust Baseline for Spotting AI-Synthesized Fake Faces
• Global Texture Enhancement for Fake Face Detection in the Wild
• Source Generator Attribution via Inversion
• GANprintR: Improved Fakes and Evaluation of the State of the Art in Face Manipulation Detection
• One-Shot GAN Generated Fake Face Detection
• Combating Disinformation in a Social Media Age
• Do Not Deceive Your Employer with a Virtual Background: A Video Conferencing Manipulation-Detection System
• Towards transformation-resilient provenance detection of digital media
• Holistic Image Manipulation Detection using Pixel Co-occurrence Matrices
• RealHD: A High-Quality Dataset for Robust Detection of State-of-the-Art AI-Generated Images