English

Discovering Transferable Forensic Features for CNN-generated Images Detection

Computer Vision and Pattern Recognition 2022-08-25 v1 Cryptography and Security Machine Learning

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 counterfeit images regardless of generator architectures, loss functions, training datasets, and resolutions. 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/

Keywords

Cite

@article{arxiv.2208.11342,
  title  = {Discovering Transferable Forensic Features for CNN-generated Images Detection},
  author = {Keshigeyan Chandrasegaran and Ngoc-Trung Tran and Alexander Binder and Ngai-Man Cheung},
  journal= {arXiv preprint arXiv:2208.11342},
  year   = {2022}
}

Comments

ECCV 2022 Oral; 35 pages

R2 v1 2026-06-25T01:55:25.204Z