Metraipolis › archive › dc_bb9853556e18

Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses — arXiv:2610.08417

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08417
License (as archived)
CC0-1.0
Archived
2026-10-07T11:35:28.639Z
SHA-256 of the archived text
ba68c4df27b7889ade588de26425a6319c8f86f8fcbac672f12f17cd283905dd
Stable URL of this page
https://metraipolis.com/documento/dc_bb9853556e18

How to cite

Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses — arXiv:2610.08417 — arXiv (en), https://arxiv.org/abs/2610.08417 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb9853556e18 (Metraipolis archive dc_bb9853556e18, sha256 ba68c4df27b7889ade588de26425a6319c8f86f8fcbac672f12f17cd283905dd)
BibTeX
@misc{dcbb9853556e18,
  title = {Ariadne's Thread of LipSync: Unraveling Forgeries via Inconsistency between Lip Motions and Head Poses — arXiv:2610.08417},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08417},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb9853556e18; sha256 ba68c4df27b7889ade588de26425a6319c8f86f8fcbac672f12f17cd283905dd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08417. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent advances in LipSync generation technology have led to the creation of highly realistic videos, posing severe societal risks. However, existing defense strategies struggle against LipSync forgeries, as advanced LipSync generation methods not only achieve better lip synchronization but also eliminate visual artifacts. An important reason is that they overlook an inherent biological coupling between lip movements and head poses in natural speech videos. In this paper, we propose LipDA, a novel framework for joint LipSync Detection and Attribution, which takes advantage of the inconsistency between head and lip. For detection, the framework learns to quantify this discrepancy by contrasting lip and pose features from authentic versus forged videos. For attribution, our method is designed to capture the unique temporal dynamics and audio-visual synchronization patterns that act as the fingerprint of models, enabling source tracing. We conduct extensive experiments on two challenging LipSync datasets as well as our own proposed large-scale and multi-generator dataset. LipDA achieves over 97\% AUC in detection and 97.5\% accuracy in model attribution, significantly outperforming existing methods. Code and the proposed LipSync-A dataset are available at this https URL .

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.08417 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T11:18:39.730Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).