Self-supervised GAN Detector
This addresses the challenge of preventing malicious use of generative models, such as fraud and fake news, by improving detection of unseen generated images, though it is an incremental advancement in GAN detection.
The paper tackles the problem of detecting unseen GAN-generated images by proposing a self-supervised framework with an artificial fingerprint generator and a GAN detector, achieving robust generalization that outperforms previous state-of-the-art methods without using GAN images from the training dataset.
Although the recent advancement in generative models brings diverse advantages to society, it can also be abused with malicious purposes, such as fraud, defamation, and fake news. To prevent such cases, vigorous research is conducted to distinguish the generated images from the real images, but challenges still remain to distinguish the unseen generated images outside of the training settings. Such limitations occur due to data dependency arising from the model's overfitting issue to the training data generated by specific GANs. To overcome this issue, we adopt a self-supervised scheme to propose a novel framework. Our proposed method is composed of the artificial fingerprint generator reconstructing the high-quality artificial fingerprints of GAN images for detailed analysis, and the GAN detector distinguishing GAN images by learning the reconstructed artificial fingerprints. To improve the generalization of the artificial fingerprint generator, we build multiple autoencoders with different numbers of upconvolution layers. With numerous ablation studies, the robust generalization of our method is validated by outperforming the generalization of the previous state-of-the-art algorithms, even without utilizing the GAN images of the training dataset.