Metraipolis › archive › dc_d28bb64793ee
Memory-Efficient Designs for Word-Wise Universal Fully Homomorphic Encryption — arXiv:2609.04769
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.04769
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T22:51:16.785Z
- SHA-256 of the archived text
e9796f9c37bbe54f50910624e825e9ba8bcbc840f6e928d7b06caf8852a2c652- Stable URL of this page
https://metraipolis.com/documento/dc_d28bb64793ee
How to cite
Memory-Efficient Designs for Word-Wise Universal Fully Homomorphic Encryption — arXiv:2609.04769 — arXiv (en), https://arxiv.org/abs/2609.04769 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d28bb64793ee (Metraipolis archive dc_d28bb64793ee, sha256 e9796f9c37bbe54f50910624e825e9ba8bcbc840f6e928d7b06caf8852a2c652)
BibTeX
@misc{dcd28bb64793ee,
title = {Memory-Efficient Designs for Word-Wise Universal Fully Homomorphic Encryption — arXiv:2609.04769},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.04769},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d28bb64793ee; sha256 e9796f9c37bbe54f50910624e825e9ba8bcbc840f6e928d7b06caf8852a2c652},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04769. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Fully Homomorphic Encryption (FHE) enables computation on encrypted data, preserving privacy throughout analysis. While its privacy is very strong, FHE is much slower to execute than the original computation. In particular, due to the recent success in accelerating its compute, the performance bottleneck shifts to the memory, especially considering that FHE magnifies the data size by orders of magnitude, resulting in a low arithmetic intensity. We propose BXT, an FHE optimization framework that mitigates the memory bottleneck through four techniques: (1) ciphertext compression, which regenerates ciphertext components from seeds during execution; (2) ciphertext serialization, which packs coefficients as bit arrays and unpacks them during L2-to-L1 transfer; (3) delayed seed generation, which defers PRNG-heavy offline work across aggregated operations; and (4) ciphertext digit pruning guided by fault-aware training tailored for Universal FHE. On CNN inference, the BXT-CSO50 configuration effectively achieves up to 3.8$\times$ speedup over the 100x GPU baseline with less than 1% accuracy loss at 50% comparison precision. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-07 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2609.04769 — 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 2026-10-16T22:30:54.309Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).