CNN Detection of GAN-Generated Face Images based on Cross-Band Co-occurrences Analysis

TL;DR

This paper introduces a CNN-based method that detects GAN-generated face images by analyzing inconsistencies in spectral band co-occurrences, outperforming previous spatial-only techniques especially after image post-processing.

Contribution

The paper presents a novel approach using cross-band co-occurrence matrices with CNNs to improve detection of GAN-generated images, especially under post-processing conditions.

Findings

Outperforms spatial-only co-occurrence detection methods.

Shows robustness against geometric transformations and filtering.

Effective in distinguishing synthetic from real face images.

Abstract

Last-generation GAN models allow to generate synthetic images which are visually indistinguishable from natural ones, raising the need to develop tools to distinguish fake and natural images thus contributing to preserve the trustworthiness of digital images. While modern GAN models can generate very high-quality images with no visible spatial artifacts, reconstruction of consistent relationships among colour channels is expectedly more difficult. In this paper, we propose a method for distinguishing GAN-generated from natural images by exploiting inconsistencies among spectral bands, with specific focus on the generation of synthetic face images. Specifically, we use cross-band co-occurrence matrices, in addition to spatial co-occurrence matrices, as input to a CNN model, which is trained to distinguish between real and synthetic faces. The results of our experiments confirm the goodness of our approach which outperforms a similar detection technique based on intra-band spatial co-occurrences only. The performance gain is particularly significant with regard to robustness against post-processing, like geometric transformations, filtering and contrast manipulations.