A universal detector of CNN-generated images using properties of checkerboard artifacts in the frequency domain

TL;DR

This paper introduces a universal CNN-generated image detector based on checkerboard artifact properties in the frequency domain, enhancing spectrum analysis and combining detectors for improved accuracy.

Contribution

It presents a novel spectrum enhancement method leveraging checkerboard artifacts and an ensemble approach that outperforms existing detectors in certain conditions.

Findings

Ensemble detector outperforms state-of-the-art methods

Checkerboard artifacts are effective features for CNN image detection

Enhanced spectrum analysis improves detection accuracy

Abstract

We propose a novel universal detector for detecting images generated by using CNNs. In this paper, properties of checkerboard artifacts in CNN-generated images are considered, and the spectrum of images is enhanced in accordance with the properties. Next, a classifier is trained by using the enhanced spectrums to judge a query image to be a CNN-generated ones or not. In addition, an ensemble of the proposed detector with emphasized spectrums and a conventional detector is proposed to improve the performance of these methods. In an experiment, the proposed ensemble is demonstrated to outperform a state-of-the-art method under some conditions.