EUVIMEDEUVIMED entdecken
Crossref

Deepfake Detection and Localization Using Multi-View Inconsistency Measurement

Bolin Zhang, Qilin Yin, Wei Lu, Xiangyang Luo

IEEE Transactions on Dependable and Secure Computing · 2025-03 · 22 (2) · 1796-1809

DOI: 10.1109/tdsc.2024.3472064 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Dependable and Secure Computing, 2025-03. Verfasst von Bolin Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Guangdong Provincial Key Laboratory of Information Security Technology, Communication University of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As deepfake technology advances, forgery detection techniques have evolved beyond simple classification to include fine-grained localization. However, existing deepfake localization methods struggle with with real-world deepfake videos, which are often multi-face scenarios with only some parts manipulated. To address the above-mentioned problems, we propose a Multi-View Inconsistency Measurement (MVIM) network that simultaneously measures inconsistencies from noise and temporal view to detect and locate tampered regions. Specifically, considering the noise inconsistencies in multi-face scenarios where fake faces have inconsistent noise patterns compared to real faces and backgrounds, we design a Noise Inconsistency Measurement (Noise-IM) module that measures noise similarity among faces and between faces and backgrounds using a masked attention mechanism to identify suspected tampered regions in noise domain. Since facial jitter of tampered regions in deepfake videos is observed to be more intense than that of real regions, we design a Temporal Inconsistency Measurement (Temporal-IM) module which adopts self-attention mechanism and fine-grained bi-direction convolutions to capture tampering traces between frames in temporal domain. Inconsistency features obtained by the two modules are fused for detecting and locating tampered regions. The superiority of our MVIM network is verified by extensive experiments with many state-of-the-art methods in different benchmark datasets.

Förderung

  • National Natural Science Foundation of China
  • Guangdong Provincial Key Laboratory of Information Security Technology
  • Communication University of China

Zitieren

APA

Zhang, B., Yin, Q., Lu, W., & Luo, X. (2025). Deepfake Detection and Localization Using Multi-View Inconsistency Measurement. IEEE Transactions on Dependable and Secure Computing, 22(2), 1796-1809. https://doi.org/10.1109/tdsc.2024.3472064

Vancouver

Zhang B, Yin Q, Lu W, Luo X. Deepfake Detection and Localization Using Multi-View Inconsistency Measurement. IEEE Transactions on Dependable and Secure Computing. 2025;22(2):1796-1809. doi:10.1109/tdsc.2024.3472064

BibTeX
@article{Zhang2025,
  author = {Zhang, Bolin and Yin, Qilin and Lu, Wei and Luo, Xiangyang},
  title = {Deepfake Detection and Localization Using Multi-View Inconsistency Measurement},
  journal = {IEEE Transactions on Dependable and Secure Computing},
  year = {2025},
  volume = {22},
  number = {2},
  pages = {1796--1809},
  doi = {10.1109/tdsc.2024.3472064}
}
Kostenlos starten →