Detecting GAN generated Fake Images using Co-occurrence Matrices

TLDR

Generative Adversarial Networks enable novel pixel transformations, and GAN‑based techniques such as Image‑to‑Image translations and DeepFakes have become popular for creating fake images. The study proposes a novel method to detect GAN‑generated fake images using co‑occurrence matrices combined with deep learning. The method extracts co‑occurrence matrices from the three color channels in the pixel domain and trains a deep convolutional neural network to classify images. The approach achieves over 99 % accuracy on both cycleGAN and StarGAN datasets and generalizes well when trained on one dataset and tested on the other.

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.