[Resource Topic] 2024/1611: Rhombus: Fast Homomorphic Matrix-Vector Multiplication for Secure Two-Party Inference

Welcome to the resource topic for 2024/1611

Title:
Rhombus: Fast Homomorphic Matrix-Vector Multiplication for Secure Two-Party Inference

Authors: Jiaxing He, Kang Yang, Guofeng Tang, Zhangjie Huang, Li Lin, Changzheng Wei, Ying Yan, Wei Wang

Abstract:

We present \textit{Rhombus}, a new secure matrix-vector multiplication (MVM) protocol in the semi-honest two-party setting, which is able to be seamlessly integrated into existing privacy-preserving machine learning (PPML) frameworks and serve as the basis of secure computation in linear layers.
\textit{Rhombus} adopts RLWE-based homomorphic encryption (HE) with coefficient encoding, which allows messages to be chosen from not only a field \mathbb{F}_p but also a ring \mathbb{Z}_{2^\ell}, where the latter supports faster computation in non-linear layers. To achieve better efficiency, we develop an input-output packing technique that reduces the communication cost incurred by HE with coefficient encoding by about 21\times, and propose a split-point picking technique that reduces the number of rotations to that sublinear in the matrix dimension. Compared to the recent protocol \textit{HELiKs} by Balla and Koushanfar (CCS’23), our implementation demonstrates that \textit{Rhombus} improves the whole performance of an MVM protocol by a factor of 7.4\times \sim 8\times, and improves the end-to-end performance of secure two-party inference of ResNet50 by a factor of 4.6\times \sim 18\times.

ePrint: https://eprint.iacr.org/2024/1611

See all topics related to this paper.

Feel free to post resources that are related to this paper below.

Example resources include: implementations, explanation materials, talks, slides, links to previous discussions on other websites.

For more information, see the rules for Resource Topics .