EUVIMEDEUVIMED entdecken
Crossref

Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection

Chenming Zhou, Jiaan Wang, Yu Li, Lei Li, Juan Cao, Sheng Tang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (42) · 36101-36109

DOI: 10.1609/aaai.v40i42.40927 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Chenming Zhou und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid evolution of generative technologies necessitates reliable methods for detecting AI-generated images. A critical limitation of current detectors is their failure to generalize to images from unseen generative models, as they often overfit to source-specific semantic cues rather than learning universal generative artifacts. To overcome this, we introduce a simple yet remarkably effective pixel-level mapping pre-processing step to disrupt the pixel value distribution of images and break the fragile, non-essential semantic patterns that detectors commonly exploit as shortcuts. This forces the detector to focus on more fundamental and generalizable high-frequency traces inherent to the image generation process. Through comprehensive experiments on GAN and diffusion-based generators, we show that our approach significantly boosts the cross-generator performance of state-of-the-art detectors. Extensive analysis further verifies our hypothesis that the disruption of semantic cues is the key to generalization.

Zitieren

APA

Zhou, C., Wang, J., Li, Y., Li, L., Cao, J., & Tang, S. (2026). Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(42), 36101-36109. https://doi.org/10.1609/aaai.v40i42.40927

Vancouver

Zhou C, Wang J, Li Y, Li L, Cao J, Tang S. Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(42):36101-36109. doi:10.1609/aaai.v40i42.40927

BibTeX
@article{Zhou2026,
  author = {Zhou, Chenming and Wang, Jiaan and Li, Yu and Li, Lei and Cao, Juan and Tang, Sheng},
  title = {Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {42},
  pages = {36101--36109},
  doi = {10.1609/aaai.v40i42.40927}
}
Kostenlos starten →