Exposing GAN-generated Faces Using Inconsistent Corneal Specular Highlights
This addresses the problem of deepfake detection for security and media verification, but it is incremental as it focuses on a specific artifact rather than a broad solution.
The paper tackled the problem of detecting GAN-generated faces by identifying inconsistent corneal specular highlights between eyes, caused by GANs' lack of physical constraints, and demonstrated an automatic method that effectively distinguishes them with qualitative and quantitative evaluations.
Sophisticated generative adversary network (GAN) models are now able to synthesize highly realistic human faces that are difficult to discern from real ones visually. In this work, we show that GAN synthesized faces can be exposed with the inconsistent corneal specular highlights between two eyes. The inconsistency is caused by the lack of physical/physiological constraints in the GAN models. We show that such artifacts exist widely in high-quality GAN synthesized faces and further describe an automatic method to extract and compare corneal specular highlights from two eyes. Qualitative and quantitative evaluations of our method suggest its simplicity and effectiveness in distinguishing GAN synthesized faces.