Skip to main navigation Skip to search Skip to main content

EYES TELL ALL: IRREGULAR PUPIL SHAPES REVEAL GAN-GENERATED FACES

  • Hui Guo
  • , Shu Hu
  • , Xin Wang
  • , Ming Ching Chang
  • , Siwei Lyu
  • SUNY Albany
  • SUNY Buffalo
  • Keya Medical

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

100 Scopus citations

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.

Original languageEnglish
Title of host publication2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2904-2908
Number of pages5
ISBN (Electronic)9781665405409
DOIs
StatePublished - 2022
Event2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022 - Hybrid, Singapore
Duration: May 22 2022May 27 2022

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2022-May
ISSN (Print)1520-6149

Conference

Conference2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022
Country/TerritorySingapore
CityHybrid
Period05/22/2205/27/22

Keywords

  • GAN faces detection
  • fake face detection
  • image forensics
  • pupil segmentation

Fingerprint

Dive into the research topics of 'EYES TELL ALL: IRREGULAR PUPIL SHAPES REVEAL GAN-GENERATED FACES'. Together they form a unique fingerprint.

Cite this