@inproceedings{f2367a7908a943a2adc140200d6d9c98,
title = "Exposing GAN-synthesized faces using landmark locations",
abstract = "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.",
keywords = "Facial landmarks, GANs, Image forensics",
author = "Xin Yang and Yuezun Li and Honggang Qi and Siwei Lyu",
note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 7th ACM Workshop on Information Hiding and Multimedia Security, IH and MMSec 2019 ; Conference date: 03-07-2019 Through 05-07-2019",
year = "2019",
month = jul,
day = "2",
doi = "10.1145/3335203.3335724",
language = "English",
series = "IH and MMSec 2019 - Proceedings of the ACM Workshop on Information Hiding and Multimedia Security",
publisher = "Association for Computing Machinery, Inc",
pages = "113--118",
booktitle = "IH and MMSec 2019 - Proceedings of the ACM Workshop on Information Hiding and Multimedia Security",
}