EUVIMEDEUVIMED entdecken
Crossref

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

Nan Zhong, Mian Zou, Yiran Xu, Zhenxing Qian, Xinpeng Zhang, Baoyuan Wu, Kede Ma

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-06 · 48 (6) · 6192-6207

DOI: 10.1109/tpami.2026.3654274 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-06. Verfasst von Nan Zhong und 6 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 110 Literaturangaben. Gefördert von: Hong Kong RGC General Research Fund, CityU Strategic Research, Guangdong Basic and Applied Basic Research Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 (e.g., camera model and scene type) and pairwise-ranking ordinal and continuous EXIF tags (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.

Förderung

  • Hong Kong RGC General Research Fund
  • CityU Strategic Research
  • Guangdong Basic and Applied Basic Research Foundation

Zitieren

APA

Zhong, N., Zou, M., Xu, Y., Qian, Z., Zhang, X., Wu, B., & Ma, K. (2026). Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(6), 6192-6207. https://doi.org/10.1109/tpami.2026.3654274

Vancouver

Zhong N, Zou M, Xu Y, Qian Z, Zhang X, Wu B, et al. Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(6):6192-6207. doi:10.1109/tpami.2026.3654274

BibTeX
@article{Zhong2026,
  author = {Zhong, Nan and Zou, Mian and Xu, Yiran and Qian, Zhenxing and Zhang, Xinpeng and Wu, Baoyuan and Ma, Kede},
  title = {Self-Supervised AI-Generated Image Detection: A Camera Metadata Perspective},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {6},
  pages = {6192--6207},
  doi = {10.1109/tpami.2026.3654274}
}
Kostenlos starten →