Identification of Deep Network Generated Images Using Disparities in Color Components

TL;DR

This paper proposes a method to identify images generated by deep networks, especially GANs, by analyzing disparities in color components, achieving high accuracy even with mismatched data or unknown models.

Contribution

The study introduces a novel color-based feature set for DNG image detection and demonstrates its effectiveness across various detection scenarios, including one-class classification.

Findings

Accurately detects DNG images in various scenarios.

Outperforms existing detection methods in mismatched data conditions.

Effective even when the GAN model is unknown, using only real images for training.

Abstract

With the powerful deep network architectures, such as generative adversarial networks, one can easily generate photorealistic images. Although the generated images are not dedicated for fooling human or deceiving biometric authentication systems, research communities and public media have shown great concerns on the security issues caused by these images. This paper addresses the problem of identifying deep network generated (DNG) images. Taking the differences between camera imaging and DNG image generation into considerations, we analyze the disparities between DNG images and real images in different color components. We observe that the DNG images are more distinguishable from real ones in the chrominance components, especially in the residual domain. Based on these observations, we propose a feature set to capture color image statistics for identifying DNG images. Additionally, we evaluate several detection situations, including the training-testing data are matched or mismatched in image sources or generative models and detection with only real images. Extensive experimental results show that the proposed method can accurately identify DNG images and outperforms existing methods when the training and testing data are mismatched. Moreover, when the GAN model is unknown, our methods also achieves good performance with one-class classification by using only real images for training.