More Real than Real: A Study on Human Visual Perception of Synthetic Faces
This addresses the problem of deep fake detection for security and media integrity, though it is incremental as it builds on existing GAN technologies.
The study investigated human ability to distinguish real faces from synthetic ones generated by advanced GANs (PG-GAN, StyleGAN, StyleGAN2), revealing that humans struggle significantly with this discrimination.
Deep fakes became extremely popular in the last years, also thanks to their increasing realism. Therefore, there is the need to measures human's ability to distinguish between real and synthetic face images when confronted with cutting-edge creation technologies. We describe the design and results of a perceptual experiment we have conducted, where a wide and diverse group of volunteers has been exposed to synthetic face images produced by state-of-the-art Generative Adversarial Networks (namely, PG-GAN, StyleGAN, StyleGAN2). The experiment outcomes reveal how strongly we should call into question our human ability to discriminate real faces from synthetic ones generated through modern AI.