Detecting GAN generated Fake Images using Co-occurrence Matrices

TL;DR

This paper presents a novel method combining co-occurrence matrices and deep CNNs to detect GAN-generated fake images, achieving over 99% accuracy and good cross-dataset generalization.

Contribution

It introduces a new approach using co-occurrence matrices with deep learning for effective GAN image detection, demonstrating high accuracy and robustness.

Findings

Achieves over 99% classification accuracy on two diverse GAN datasets.

Generalizes well across different datasets when trained on one and tested on another.

Effective in detecting GAN-generated images from various manipulation techniques.

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.