Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints
This addresses visual forensics and model attribution challenges for detecting GAN-generated images, though it is incremental as it builds on existing GAN technology.
The study tackled the problem of attributing fake images to specific GAN models by learning and analyzing GAN fingerprints, achieving consistent outperformance over baselines in various setups for image attribution and source identification.
Recent advances in Generative Adversarial Networks (GANs) have shown increasing success in generating photorealistic images. But they also raise challenges to visual forensics and model attribution. We present the first study of learning GAN fingerprints towards image attribution and using them to classify an image as real or GAN-generated. For GAN-generated images, we further identify their sources. Our experiments show that (1) GANs carry distinct model fingerprints and leave stable fingerprints in their generated images, which support image attribution; (2) even minor differences in GAN training can result in different fingerprints, which enables fine-grained model authentication; (3) fingerprints persist across different image frequencies and patches and are not biased by GAN artifacts; (4) fingerprint finetuning is effective in immunizing against five types of adversarial image perturbations; and (5) comparisons also show our learned fingerprints consistently outperform several baselines in a variety of setups.