Eyes Tell All: Irregular Pupil Shapes Reveal GAN-generated Faces
This addresses the issue of identifying fake online profiles for social media users and security applications, but it is incremental as it builds on known artifacts in GAN-generated images.
The paper tackled the problem of detecting GAN-generated faces used for fake social media accounts by identifying irregular pupil shapes caused by the lack of physiological constraints in GAN models, demonstrating that this artifact is widespread and developing an automatic method for detection with qualitative and quantitative evaluations showing its simplicity and effectiveness.
Generative adversary network (GAN) generated high-realistic human faces have been used as profile images for fake social media accounts and are visually challenging to discern from real ones. In this work, we show that GAN-generated faces can be exposed via irregular pupil shapes. This phenomenon is caused by the lack of physiological constraints in the GAN models. We demonstrate that such artifacts exist widely in high-quality GAN-generated faces and further describe an automatic method to extract the pupils from two eyes and analysis their shapes for exposing the GAN-generated faces. Qualitative and quantitative evaluations of our method suggest its simplicity and effectiveness in distinguishing GAN-generated faces.