Exposing GAN-synthesized Faces Using Landmark Locations
This addresses the need for detecting fake faces in security and media, but it is incremental as it builds on known differences in GAN-generated facial configurations.
The paper tackled the problem of detecting GAN-synthesized faces by analyzing facial landmark locations, achieving good classification performance with an SVM classifier.
Generative adversary networks (GANs) have recently led to highly realistic image synthesis results. In this work, we describe a new method to expose GAN-synthesized images using the locations of the facial landmark points. Our method is based on the observations that the facial parts configuration generated by GAN models are different from those of the real faces, due to the lack of global constraints. We perform experiments demonstrating this phenomenon, and show that an SVM classifier trained using the locations of facial landmark points is sufficient to achieve good classification performance for GAN-synthesized faces.