Skip to main navigation Skip to search Skip to main content

Forensics Forest: Multi-scale Hierarchical Cascade Forest for Detecting GAN-generated Faces

  • Jiucui Lu
  • , Yuezun Li
  • , Jiaran Zhou
  • , Bin Li
  • , Siwei Lyu

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

3 Scopus citations

Abstract

We describe a simple and effective method called ForensicsForest to detect GAN-generate faces. Instead of using the commonly used CNN models, we describe a novel multi-scale hierarchical cascade forest, which takes semantic and frequency features as input, and hierarchically cascades different levels of features for authenticity prediction. We then propose a multi-scale ensemble, which comprehensively considers different levels of information to improve the performance further. Our method is validated on state-of-the-art GAN-generated face datasets in comparison with several CNN models, which demonstrates the surprising effectiveness of our method in detecting GAN-generated faces.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE International Conference on Multimedia and Expo, ICME 2023
PublisherIEEE Computer Society
Pages2309-2314
Number of pages6
ISBN (Electronic)9781665468916
DOIs
StatePublished - 2023
Event2023 IEEE International Conference on Multimedia and Expo, ICME 2023 - Brisbane, Australia
Duration: Jul 10 2023Jul 14 2023

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
Volume2023-July

Conference

Conference2023 IEEE International Conference on Multimedia and Expo, ICME 2023
Country/TerritoryAustralia
CityBrisbane
Period07/10/2307/14/23

Keywords

  • Digital forensics
  • GAN-generated faces detection
  • Random forest

Fingerprint

Dive into the research topics of 'Forensics Forest: Multi-scale Hierarchical Cascade Forest for Detecting GAN-generated Faces'. Together they form a unique fingerprint.

Cite this