Metraipolis › archive › dc_6b93a1cbd2bd
Encrypt What Matters: When Selective Homomorphic Inference Is Efficient — arXiv:2609.09357
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09357
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:54:36.357Z
- SHA-256 of the archived text
ef2956d321013a5c0d01ae270737e0d8442eb87b24e457cb77949524773cccf8- Stable URL of this page
https://metraipolis.com/documento/dc_6b93a1cbd2bd
How to cite
Encrypt What Matters: When Selective Homomorphic Inference Is Efficient — arXiv:2609.09357 — arXiv (en), https://arxiv.org/abs/2609.09357 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6b93a1cbd2bd (Metraipolis archive dc_6b93a1cbd2bd, sha256 ef2956d321013a5c0d01ae270737e0d8442eb87b24e457cb77949524773cccf8)
BibTeX
@misc{dc6b93a1cbd2bd,
title = {Encrypt What Matters: When Selective Homomorphic Inference Is Efficient — arXiv:2609.09357},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09357},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6b93a1cbd2bd; sha256 ef2956d321013a5c0d01ae270737e0d8442eb87b24e457cb77949524773cccf8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09357. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fully homomorphic encryption (FHE) enables inference on private data without revealing it to the server, but evaluating an entire input under FHE is expensive. We study \emph{selective homomorphic inference}, where only a sensitive region of interest (ROI) is encrypted, and computations independent of that region are performed in plaintext. Selective evaluation produces the same output as full FHE on the same model, without retraining. Its efficiency depends on how quickly encrypted dependencies spread through the network. For small encrypted ROIs, locality-preserving architectures can achieve order-of-magnitude homomorphic-evaluation speedups, whereas architectures with early global mixing provide essentially no speedup. These results identify locality as the key architectural property governing the benefit of selective homomorphic inference.
Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.09357 — 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 2026-10-16T07:37:41.546Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).