@inproceedings{763a464e5db54eca8f3b7079e1713458,
title = "EYES TELL ALL: IRREGULAR PUPIL SHAPES REVEAL GAN-GENERATED FACES",
abstract = "Generative adversarial network (GAN) generated high-realistic human faces are visually challenging to discern from real ones. They have been used as profile images for fake social media accounts, which leads to high negative social impacts. 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. We design an automatic method to segment the pupils from the eyes and analyze their shapes to distinguish GAN-generated faces from real ones. Qualitative and quantitative evaluations of our method on the Flickr-Faces-HQ dataset and a StyleGAN2 generated face dataset demonstrate the effectiveness and simplicity of our method.",
keywords = "GAN faces detection, fake face detection, image forensics, pupil segmentation",
author = "Hui Guo and Shu Hu and Xin Wang and Chang, \{Ming Ching\} and Siwei Lyu",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE; 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022 ; Conference date: 22-05-2022 Through 27-05-2022",
year = "2022",
doi = "10.1109/ICASSP43922.2022.9746597",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2904--2908",
booktitle = "2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings",
address = "United States",
}