-
[pdf]
[bibtex]@InProceedings{Guarnera_2022_CVPR, author = {Guarnera, Luca and Giudice, Oliver and Nie{\ss}ner, Matthias and Battiato, Sebastiano}, title = {On the Exploitation of Deepfake Model Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2022}, pages = {61-70} }
On the Exploitation of Deepfake Model Recognition
Abstract
Despite recent advances in Generative Adversarial Networks (GANs), with special focus to the Deepfake phenomenon there is no a clear understanding neither in terms of explainability nor of recognition of the involved models. In particular, the recognition of a specific GAN model that generated the deepfake image compared to many other possible models created by the same generative architecture (e.g. StyleGAN) is a task not yet completely addressed in the state-of-the-art. In this work, a robust processing pipeline to evaluate the possibility to point-out analytic fingerprints for Deepfake model recognition is presented. After exploiting the latent space of 50 slightly different models through an in-depth analysis on the generated images, a proper encoder was trained to discriminate among these models obtaining a classification accuracy of over 96%. Once demonstrated the possibility to discriminate extremely similar images, a dedicated metric exploiting the insights discovered in the latent space was introduced. By achieving a final accuracy of more than 94% for the Model Recognition task on images generated by models not employed in the training phase, this study takes an important step in countering the Deepfake phenomenon introducing a sort of signature in some sense similar to those employed in the multimedia forensics field (e.g. for camera source identification task, image ballistics task, etc).
Related Material