EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning the Manifold of Authenticity: Hybrid-Curvature Representation Learning for Generalizable Deepfake Detection

Nicolas Larue, Vitomir Štruc, Peter Peer, Ngoc-Son Vu

IEEE Access · 2026 · 14 · 101988-102001

DOI: 10.1109/access.2026.3702429 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Nicolas Larue und 3 weiteren Autor:innen. Die Arbeit nennt 81 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Slovenian Research and Innovation Agency, DeepFake DAD Project, EUTOPIA Ph.D. Funding Scheme.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • Slovenian Research and Innovation Agency
  • DeepFake DAD Project
  • EUTOPIA Ph.D. Funding Scheme

Zitieren

APA

Larue, N., Štruc, V., Peer, P., & Vu, N. (2026). Learning the Manifold of Authenticity: Hybrid-Curvature Representation Learning for Generalizable Deepfake Detection. IEEE Access, 14, 101988-102001. https://doi.org/10.1109/access.2026.3702429

Vancouver

Larue N, Štruc V, Peer P, Vu N. Learning the Manifold of Authenticity: Hybrid-Curvature Representation Learning for Generalizable Deepfake Detection. IEEE Access. 2026;14:101988-102001. doi:10.1109/access.2026.3702429

BibTeX
@article{Larue2026,
  author = {Larue, Nicolas and Štruc, Vitomir and Peer, Peter and Vu, Ngoc-Son},
  title = {Learning the Manifold of Authenticity: Hybrid-Curvature Representation Learning for Generalizable Deepfake Detection},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {101988--102001},
  doi = {10.1109/access.2026.3702429}
}
Kostenlos starten →