Singapore Institute of Technology
Browse
2208.11342.pdf (12.81 MB)

Discovering Transferable Forensic Features for CNN-generated Images Detection

Download (12.81 MB)
conference contribution
posted on 2023-11-08, 08:22 authored by Keshigeyan Chandrasegaran, Ngoc-Trung Tran, Alexander BinderAlexander Binder, Cheung Ngai-Man

Abstract. Visual counterfeits are increasingly causing an existential conundrum in mainstream media with rapid evolution in neural image synthesis methods. Though detection of such counterfeits has been a taxing problem in the image forensics community, a recent class of forensic detectors – universal detectors – are able to surprisingly spot counter-feit images regardless of generator architectures, loss functions, training datasets, and resolutions [61]. This intriguing property suggests the possible existence of transferable forensic features (T-FF) in universal detectors. In this work, we conduct the first analytical study to discover and understand T-FF in universal detectors. Our contributions are 2-fold: 1) We propose a novel forensic feature relevance statistic (FF-RS) to quantify and discover T-FF in universal detectors and, 2) Our qualitative and quantitative investigations uncover an unexpected finding: color is a critical T-FF in universal detectors. Code and models are available at https://keshik6.github.io/transferable-forensic-features/ .

History

Journal/Conference/Book title

ECCV 2022

Publication date

2022-10-01

Version

  • Post-print

Sub-Item type

  • Magazine article

Usage metrics

    Categories

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC