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.

Cite

Text

Mundra et al. "Exposing GAN-Generated Profile Photos from Compact Embeddings." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023. doi:10.1109/CVPRW59228.2023.00095

Markdown

[Mundra et al. "Exposing GAN-Generated Profile Photos from Compact Embeddings." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2023.](https://mlanthology.org/cvprw/2023/mundra2023cvprw-exposing/) doi:10.1109/CVPRW59228.2023.00095

BibTeX

@inproceedings{mundra2023cvprw-exposing,
  title     = {{Exposing GAN-Generated Profile Photos from Compact Embeddings}},
  author    = {Mundra, Shivansh and Porcile, Gonzalo J. Aniano and Marvaniya, Smit and Verbus, James R. and Farid, Hany},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2023},
  pages     = {884-892},
  doi       = {10.1109/CVPRW59228.2023.00095},
  url       = {https://mlanthology.org/cvprw/2023/mundra2023cvprw-exposing/}
}