-
[pdf]
[bibtex]@InProceedings{Mundra_2023_CVPR, author = {Mundra, Shivansh and Porcile, Gonzalo J. Aniano and Marvaniya, Smit and Verbus, James R. and Farid, Hany}, title = {Exposing GAN-Generated Profile Photos From Compact Embeddings}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops}, month = {June}, year = {2023}, pages = {884-892} }
Exposing GAN-Generated Profile Photos From Compact Embeddings
Abstract
Generative adversarial networks (GANs) have been used to create remarkably realistic images of people. More recently, diffusion-based techniques have taken image synthesis to the next level. From only a text prompt, these techniques can synthesize any image seemingly limited only by our imagination. Along with the many clever and creative use cases, synthetically-generated faces are being used to create more convincing fake social-media profiles. We describe two related techniques that learn low-dimensional (128-D) embeddings of GAN-generated faces. We show that these embeddings capture common facial structures found in these synthetically-generated faces that are uncommon in real profile photos. These low-dimensional models, trained on a relatively small data set, achieve higher classification performance than larger and more complex state-of-the-art classifiers.
Related Material