2D-FACT: Dual-Domain Fake Image Detection Against Text-To-Image Generative Models

Eric Ji, Boxiang Dong, Bharath Samanthula, Na Zhou

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

Abstract

Recent developments in generative artificial intelligence are bringing great concerns for privacy, security and misinformation. Our work focuses on the detection of fake images generated by text-To-image models. We propose a dual-domain CNN-based classifier that utilizes image features in both the spatial and frequency domain. Through an extensive set of experiments, we demonstrate that the frequency domain features facilitate high accuracy, zero-Transfer learning between different generative models, and faster convergence. To our best knowledge, this is the first effective detector against generative models that are finetuned for a specific subject.

Original languageEnglish
Title of host publicationIEEE MIT Undergraduate Research Technology Conference, URTC 2023 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350308600
DOIs
StatePublished - 2023
Event2023 IEEE MIT Undergraduate Research Technology Conference, URTC 2023 - Hybrid, Cambridge, United States
Duration: 6 Oct 20238 Oct 2023

Publication series

NameIEEE MIT Undergraduate Research Technology Conference, URTC 2023 - Proceedings

Conference

Conference2023 IEEE MIT Undergraduate Research Technology Conference, URTC 2023
Country/TerritoryUnited States
CityHybrid, Cambridge
Period6/10/238/10/23

Keywords

  • AI generative model
  • fake image detection
  • frequency domain

Fingerprint

Dive into the research topics of '2D-FACT: Dual-Domain Fake Image Detection Against Text-To-Image Generative Models'. Together they form a unique fingerprint.

Cite this