Metraipolis › archive › dc_0fc42c253d30
OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design — arXiv:2609.16898
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.16898
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T19:29:47.709Z
- SHA-256 of the archived text
c52bec6e7a7f6a4a1429122872d3390133c0de18651051decf5892b281c844c2- Stable URL of this page
https://metraipolis.com/documento/dc_0fc42c253d30
How to cite
OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design — arXiv:2609.16898 — arXiv (en), https://arxiv.org/abs/2609.16898 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0fc42c253d30 (Metraipolis archive dc_0fc42c253d30, sha256 c52bec6e7a7f6a4a1429122872d3390133c0de18651051decf5892b281c844c2)
BibTeX
@misc{dc0fc42c253d30,
title = {OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design — arXiv:2609.16898},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.16898},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0fc42c253d30; sha256 c52bec6e7a7f6a4a1429122872d3390133c0de18651051decf5892b281c844c2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16898. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Private deep neural network (DNN) inference based on hybrid homomorphic encryption (HE) and multi-party computation (MPC) can protect user data with a formal guarantee, but at the cost of significant latency overhead due to HE. Customized HE accelerators have been proposed and have achieved orders-of-magnitude speedup for individual HE operations. However, when directly applying a commercial HE accelerator to state-of-the-art HE-MPC frameworks, we observe only limited end-to-end performance gain. This is because HE-MPC frameworks often require wireless transmission of input and output ciphertexts for each HE operation, leading to a severe network communication bottleneck. To overcome this challenge, we introduce OptiPrime, a protocol-hardware co-optimization framework for efficient private DNN inference. OptiPrime features a novel HE protocol for convolutions that substantially reduces the number of transmitted output ciphertexts and mitigates the network communication bottleneck. Meanwhile, as the new protocol introduces complex computation for fewer output ciphertext, we observe new memory access challenges due to a high volume of weight plaintexts and intermediate ciphertexts. Hence, we further propose a lightweight compression system for the weight plaintexts, reducing memory traffic by 10 times, as well as a specialized dataflow to maximize on-chip data reuse of intermediate ciphertexts. Extensive experiments show that our framework outperforms the Cheetah baseline by at most 5.7 times on CPUs and 4.2 times with an accelerator. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AR). Categorie arXiv: Hardware Architecture (cs.AR) ; Cryptography and Security (cs.CR); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.16898 — 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 2026-10-15T18:35:20.271Z dalla pagina https://arxiv.org/catchup/cs.AR/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).