EUVIMEDEUVIMED entdecken
Crossref

HFGA ‐Net: High‐frequency guided attention network for deepfake detection and localization

Qizhi Gao, Gen Li, Teng Zhang, Huawei Tian, Yun Cao

Journal of Forensic Sciences · 2026-11 · 71 (6) · 2760-2771

DOI: 10.1111/1556-4029.70415 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Forensic Sciences, online erschienen am 22.07.2026. Verfasst von Qizhi Gao und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Information and Cyber Security, People's Public Security University of China, Beijing, China. Die Arbeit nennt 50 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The application of deepfake for video and image manipulation has raised severe trust issues and security concerns in modern society. Prior research has revealed that the high‐frequency components of forged images exhibit distinctive forensic artifacts. Motivated by this, we propose a novel deepfake detection and localization approach called High‐Frequency Guided Attention Network (HFGA‐Net), which enhances the detection of forged faces by leveraging high‐frequency information to capture fine‐grained forgery cues. Specifically, to better extract and encode the fine‐grained forgery cues, we first propose the Frequency‐Guided Patch‐wise Attention (FGPA). The FGPA captures high‐frequency information in shallow features. Furthermore, we design the Dynamic High‐Frequency Multi‐Stage Attention (DHFMA) to capture high‐frequency information from multi‐stage features. Additionally, to address the critical scarcity of pixel‐level annotations for forged regions in existing datasets, we propose a morphology‐based mask generation method. Extensive experiments demonstrate that our proposed method exhibits strong generalization across diverse datasets on both detection and localization tasks.

Schlagwörter

Stichwörter der Autor:innen

contrastive learningdeepfake detectiondeepfake localizationface forensicshigh‐frequency informationmulti‐stage attention

Autor:innen und Institutionen

  • College of Information and Cyber Security, People's Public Security University of China, Beijing, China.
  • Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China.

Förderung

  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Gao, Q., Li, G., Zhang, T., Tian, H., & Cao, Y. (2026). HFGA ‐Net: High‐frequency guided attention network for deepfake detection and localization. Journal of Forensic Sciences, 71(6), 2760-2771. https://doi.org/10.1111/1556-4029.70415

Vancouver

Gao Q, Li G, Zhang T, Tian H, Cao Y. HFGA ‐Net: High‐frequency guided attention network for deepfake detection and localization. Journal of Forensic Sciences. 2026;71(6):2760-2771. doi:10.1111/1556-4029.70415

BibTeX
@article{Gao2026,
  author = {Gao, Qizhi and Li, Gen and Zhang, Teng and Tian, Huawei and Cao, Yun},
  title = {HFGA ‐Net: High‐frequency guided attention network for deepfake detection and localization},
  journal = {Journal of Forensic Sciences},
  year = {2026},
  volume = {71},
  number = {6},
  pages = {2760--2771},
  doi = {10.1111/1556-4029.70415}
}
Kostenlos starten →