Metraipolis › archive › dc_7121c0f8d8ec
Semantic Privacy Protection with Utility Preservation for 3D Point Clouds — arXiv:2609.13823
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13823
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T01:52:46.976Z
- SHA-256 of the archived text
576267455c420e3000a02d7792373d972f60e28206ecf055261ed35dcda96bd2- Stable URL of this page
https://metraipolis.com/documento/dc_7121c0f8d8ec
How to cite
Semantic Privacy Protection with Utility Preservation for 3D Point Clouds — arXiv:2609.13823 — arXiv (en), https://arxiv.org/abs/2609.13823 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7121c0f8d8ec (Metraipolis archive dc_7121c0f8d8ec, sha256 576267455c420e3000a02d7792373d972f60e28206ecf055261ed35dcda96bd2)
BibTeX
@misc{dc7121c0f8d8ec,
title = {Semantic Privacy Protection with Utility Preservation for 3D Point Clouds — arXiv:2609.13823},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13823},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7121c0f8d8ec; sha256 576267455c420e3000a02d7792373d972f60e28206ecf055261ed35dcda96bd2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13823. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Point cloud data face serious semantic privacy risks during acquisition, transmission, and cross-institutional sharing. Existing methods mostly rely on geometric perturbation or destructive encryption, which can reduce the recognizability of the original class but often impair downstream usability. This paper proposes a class-transfer-based semantic encryption framework for point clouds, aiming to conceal original class information while preserving task utility and supporting authorized recovery. Specifically, we construct a unified latent space with a shared-backbone Normalizing Flow, and combine LoRA and FiLM to achieve parameter-efficient class-conditional adaptation. We further introduce diffusion-guided flow alignment to regularize the latent distribution, construct an energy-based category transition graph, and obtain an optimal class-transfer table through global matching. Then, a latent-space Neural ODE continuously evolves source-class latents into target-class latents, which are decoded into target-class point clouds through the inverse flow. We adopt attacker-oriented metrics, including New-Class Recognition Rate (NCRR), Original-Class Leakage Rate (OCLR), and Original Label Recovery Rate (OLRR), to evaluate privacy and utility. Experiments on classification and segmentation benchmarks show that the proposed method achieves controllable semantic transformation, effectively reduces original-class semantic leakage, preserves downstream learnability in the protected domain, and supports reliable authorized reconstruction. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.13823 — 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 2026-10-16T01:25:23.533Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).