Fingerprints of Super Resolution Networks

Several recent studies have demonstrated that deep-learning based image generation models, such as GANs, can be uniquely identified, and possibly even reverse engineered, by the fingerprints they leave on their output images. We extend this research to a previously unstudied type of image generator: single image super-resolution (SISR) networks. Compared to previously studied models, SISR networks are a uniquely challenging class of image generation model from which to extract and analyze fingerprints, as they can often generate images that closely match the corresponding ground truth and thus likely leave little flexibility to embed signatures. We take SISR models as examples to investigate if the findings from the previous work on fingerprints of GAN-based networks are valid for general image generation models. In this paper, we present an analysis of the capabilities and limitations of model fingerprinting in this domain. We show that SISR networks with a high upscaling factor or trained using adversarial loss leave highly distinctive fingerprints, and show promising results for reverse engineering some hyperparameters of SISR networks, including scale and loss function.