On the generalization of GAN image forensics
This addresses the need for forensic models to generalize across new GAN types to ensure visual content credibility, but it is incremental as it builds on existing CNN-based detection methods.
The paper tackles the problem of generalization in GAN image forensics by proposing a method using preprocessed images to train a CNN model, which learns more intrinsic features to classify real and fake face images, with experimental results proving its effectiveness.
Recently the GAN generated face images are more and more realistic with high-quality, even hard for human eyes to detect. On the other hand, the forensics community keeps on developing methods to detect these generated fake images and try to guarantee the credibility of visual contents. Although researchers have developed some methods to detect generated images, few of them explore the important problem of generalization ability of forensics model. As new types of GANs are emerging fast, the generalization ability of forensics models to detect new types of GAN images is absolutely an essential research topic. In this paper, we explore this problem and propose to use preprocessed images to train a forensic CNN model. By applying similar image level preprocessing to both real and fake training images, the forensics model is forced to learn more intrinsic features to classify the generated and real face images. Our experimental results also prove the effectiveness of the proposed method.