Metraipolis › archive › dc_660a762aa540

Audio-Driven Adversarial Defense for 3D Talking Face Generation with totally Visual Fidelity Preservation — arXiv:2608.30951

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30951
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:44.296Z
SHA-256 of the archived text
fd902c4ca3be2ef0f62d73427f142d4e665f4d32cf6ec71dcbfdadf7af719f4f
Stable URL of this page
https://metraipolis.com/documento/dc_660a762aa540

How to cite

Audio-Driven Adversarial Defense for 3D Talking Face Generation with totally Visual Fidelity Preservation — arXiv:2608.30951 — arXiv (en), https://arxiv.org/abs/2608.30951 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_660a762aa540 (Metraipolis archive dc_660a762aa540, sha256 fd902c4ca3be2ef0f62d73427f142d4e665f4d32cf6ec71dcbfdadf7af719f4f)
BibTeX
@misc{dc660a762aa540,
  title = {Audio-Driven Adversarial Defense for 3D Talking Face Generation with totally Visual Fidelity Preservation — arXiv:2608.30951},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30951},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_660a762aa540; sha256 fd902c4ca3be2ef0f62d73427f142d4e665f4d32cf6ec71dcbfdadf7af719f4f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30951. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The rapid development of generative portrait models has raised growing concerns about privacy leakage and identity misuse. In particular, audio-driven 3D talking face generation can reconstruct a reusable 3D portrait of a target person from a monocular video and animate it with arbitrary speech, making realistic identity impersonation alarmingly practical. Existing proactive defenses mainly operate in the visual domain by injecting subtle perturbations into acial regions to disrupt identity acquisition. However, such perturbations often compromise visual quality due to the strong structural priors and social sensitivity of human faces, and are easily weakened by common real-world transformations such as resizing. To overcome these limitations, we propose an imperceptible audio defense for audio-driven 3D talking face generation by shifting protection from the visual modality to the audio modality. Specifically,we exploit psychoacoustic masking to hide protective perturbations within perceptually masked frequency regions of the speech signal, thereby reducing perceptual distortion while suppressing reliable facial animation. Extensive experiments demonstrate that the proposed method effectively degrades 3D talking face generation while preserving favorable perceptual quality. These findings highlight psychoacoustically guided audio perturbations as a practical and promising direction for privacy-preserving portrait protection.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.30951 — 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 2026-10-17T09:28:48.203Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).