Metraipolis › archive › dc_242552bbff9a

TADP: Dual-Branch Temporally Adaptive Differential Privacy for Expression-Aware Video Anonymization — arXiv:2610.41642

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41642
License (as archived): CC0-1.0
Archived: 2026-11-02T05:03:44.503Z
SHA-256 of the archived text: 40e6fc5207deb8428058d409c2fb9d0e0e2aedbb75152af11d80122bfc5f5d06
Stable URL of this page: https://metraipolis.com/documento/dc_242552bbff9a

How to cite

TADP: Dual-Branch Temporally Adaptive Differential Privacy for Expression-Aware Video Anonymization — arXiv:2610.41642 — arXiv (en), https://arxiv.org/abs/2610.41642 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_242552bbff9a (Metraipolis archive dc_242552bbff9a, sha256 40e6fc5207deb8428058d409c2fb9d0e0e2aedbb75152af11d80122bfc5f5d06)

BibTeX

@misc{dc242552bbff9a,
  title = {TADP: Dual-Branch Temporally Adaptive Differential Privacy for Expression-Aware Video Anonymization — arXiv:2610.41642},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41642},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_242552bbff9a; sha256 40e6fc5207deb8428058d409c2fb9d0e0e2aedbb75152af11d80122bfc5f5d06},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41642. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present TADP, a temporally adaptive differential privacy (DP) framework for inference-time privacy-preserving video generation under fixed-length clip-replacement adjacency. TADP uses a dual-branch design to extract identity and expression representations, clips and privatizes both branches with temporally adaptive Gaussian mechanisms whose noise scales depend only on preceding privatized releases within the same clip and are bounded below by history-uniform calibrated minima, and accounts for their joint release via adaptive Rényi Differential Privacy (RDP) composition. The clip-level RDP guarantee is converted to $(\varepsilon,\delta)$-differential privacy, while soft quantization and subsequent temporal processing are applied only after privatization as DP post-processing. Experiments on facial expression datasets show reduced identity leakage under evaluated attacks, usable perceptual quality and temporal stability, and high facial expression recognition utility relative to the evaluated privacy-preserving baselines. TADP formally satisfies clip-level DP and empirically provides a favorable privacy--utility trade-off under the evaluated threat models and datasets.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41642 — 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 2026-11-02T04:49:13.265Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).