EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SCADET: A detection framework for AI-generated artwork integrating dynamic frequency attention and contrastive spectral analysis

Xiaolong Zhang iD, Zekai Yu iD, Jianqiao Zhao

PLOS One · 2025

DOI: 10.1371/journal.pone.0336328 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Xiaolong Zhang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Art and Design, Xihua University, Chengdu, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Artificial Intelligence, Art. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Young Scholars’ support plan of Xihua University..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With the rapid development of generative AI technology, AI-generated images pose significant challenges for authenticity verification and originality validation. This paper proposes SCADET, a novel detection framework that integrates Dynamic Frequency Attention Network (DFAN) and Contrastive Spectral Analysis Network (CSAN). DFAN adaptively analyzes image frequency domain features and dynamically adjusts attention for different artistic styles, while CSAN establishes discriminative feature spaces through contrastive learning to enhance cross-model generalization capabilities. Comprehensive experiments on the AI-ArtBench dataset demonstrate that SCADET achieves AUC values of 0.962 and 0.801 in full image and local image detection tasks respectively, representing substantial improvements of 30.5% and 34.4% over baseline methods. Cross-model evaluation shows that the framework maintains stable performance across various generation techniques, with an average accuracy of 0.81 and low variance. Ablation studies validate the effectiveness of both DFAN and CSAN components. These results advance the field of AI-generated content detection and provide valuable insights for addressing authenticity challenges in digital media applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedArtificial IntelligenceArtHumansAlgorithmsAttentionNeural Networks, Computer

Autor:innen und Institutionen

  • School of Art and Design, Xihua University, Chengdu, China.
  • School of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, China.
  • Faculty of Fine and Applied Arts and Cultural Science, Mahasarakham University, Maha Sarakham, Thailand.

ORCID-Profile: Xiaolong Zhang, Zekai Yu

Förderung

  • Young Scholars’ support plan of Xihua University.

Zitieren

APA

Zhang, X., Yu, Z., & Zhao, J. (2025). SCADET: A detection framework for AI-generated artwork integrating dynamic frequency attention and contrastive spectral analysis. PLOS One. https://doi.org/10.1371/journal.pone.0336328

Vancouver

Zhang X, Yu Z, Zhao J. SCADET: A detection framework for AI-generated artwork integrating dynamic frequency attention and contrastive spectral analysis. PLOS One. 2025. doi:10.1371/journal.pone.0336328

BibTeX
@article{Zhang2025,
  author = {Zhang, Xiaolong and Yu, Zekai and Zhao, Jianqiao},
  title = {SCADET: A detection framework for AI-generated artwork integrating dynamic frequency attention and contrastive spectral analysis},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0336328}
}
Kostenlos starten →