General GAN-generated image detection by data augmentation in fingerprint domain

TL;DR

This paper proposes a novel data augmentation method in the fingerprint domain to enhance the generalizability of GAN-generated image detectors, outperforming existing methods in cross-GAN detection tasks.

Contribution

It introduces the first data augmentation approach in the fingerprint domain, improving detector robustness against unknown GANs.

Findings

Enhanced detection accuracy in cross-GAN scenarios

Effective imitation of diverse GAN fingerprints

Superior performance over state-of-the-art methods

Abstract

In this work, we investigate improving the generalizability of GAN-generated image detectors by performing data augmentation in the fingerprint domain. Specifically, we first separate the fingerprints and contents of the GAN-generated images using an autoencoder based GAN fingerprint extractor, followed by random perturbations of the fingerprints. Then the original fingerprints are substituted with the perturbed fingerprints and added to the original contents, to produce images that are visually invariant but with distinct fingerprints. The perturbed images can successfully imitate images generated by different GANs to improve the generalization of the detectors, which is demonstrated by the spectra visualization. To our knowledge, we are the first to conduct data augmentation in the fingerprint domain. Our work explores a novel prospect that is distinct from previous works on spatial and frequency domain augmentation. Extensive cross-GAN experiments demonstrate the effectiveness of our method compared to the state-of-the-art methods in detecting fake images generated by unknown GANs.