Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Zhong, Nan, Zou, Mian, Xu, Yiran, Qian, Zhenxing, Zhang, Xinpeng, Wu, Baoyuan, Ma, Kede
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914357227552768
author Zhong, Nan
Zou, Mian
Xu, Yiran
Qian, Zhenxing
Zhang, Xinpeng
Wu, Baoyuan
Ma, Kede
author_facet Zhong, Nan
Zou, Mian
Xu, Yiran
Qian, Zhenxing
Zhang, Xinpeng
Wu, Baoyuan
Ma, Kede
contents The proliferation of AI-generated imagery poses escalating challenges for multimedia forensics, yet many existing detectors depend on assumptions about the internals of specific generative models, limiting their cross-model applicability. We introduce a self-supervised approach for detecting AI-generated images that leverages camera metadata -- specifically exchangeable image file format (EXIF) tags -- to learn features intrinsic to digital photography. Our pretext task trains a feature extractor solely on camera-captured photographs by classifying categorical EXIF tags (\emph{e.g.}, camera model and scene type) and pairwise-ranking ordinal and continuous EXIF tags (\emph{e.g.}, focal length and aperture value). Using these EXIF-induced features, we first perform one-class detection by modeling the distribution of photographic images with a Gaussian mixture model and flagging low-likelihood samples as AI-generated. We then extend to binary detection that treats the learned extractor as a strong regularizer for a classifier of the same architecture, operating on high-frequency residuals from spatially scrambled patches. Extensive experiments across various generative models demonstrate that our EXIF-induced detectors substantially advance the state of the art, delivering strong generalization to in-the-wild samples and robustness to common benign image perturbations. The code and model are publicly available at https://github.com/Ekko-zn/SDAIE.
format Preprint
id arxiv_https___arxiv_org_abs_2512_05651
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective
Zhong, Nan
Zou, Mian
Xu, Yiran
Qian, Zhenxing
Zhang, Xinpeng
Wu, Baoyuan
Ma, Kede
Computer Vision and Pattern Recognition
The proliferation of AI-generated imagery poses escalating challenges for multimedia forensics, yet many existing detectors depend on assumptions about the internals of specific generative models, limiting their cross-model applicability. We introduce a self-supervised approach for detecting AI-generated images that leverages camera metadata -- specifically exchangeable image file format (EXIF) tags -- to learn features intrinsic to digital photography. Our pretext task trains a feature extractor solely on camera-captured photographs by classifying categorical EXIF tags (\emph{e.g.}, camera model and scene type) and pairwise-ranking ordinal and continuous EXIF tags (\emph{e.g.}, focal length and aperture value). Using these EXIF-induced features, we first perform one-class detection by modeling the distribution of photographic images with a Gaussian mixture model and flagging low-likelihood samples as AI-generated. We then extend to binary detection that treats the learned extractor as a strong regularizer for a classifier of the same architecture, operating on high-frequency residuals from spatially scrambled patches. Extensive experiments across various generative models demonstrate that our EXIF-induced detectors substantially advance the state of the art, delivering strong generalization to in-the-wild samples and robustness to common benign image perturbations. The code and model are publicly available at https://github.com/Ekko-zn/SDAIE.
title Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.05651