Secure Sparse Matrix Multiplications and their Applications to Privacy-Preserving Machine Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Damie, Marc, Hahn, Florian, Peter, Andreas, Ramon, Jan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908860916170752
author Damie, Marc
Hahn, Florian
Peter, Andreas
Ramon, Jan
author_facet Damie, Marc
Hahn, Florian
Peter, Andreas
Ramon, Jan
contents To preserve data privacy, multi-party computation (MPC) enables executing Machine Learning (ML) algorithms on private data. However, MPC frameworks do not include optimized operations on sparse data. This absence makes them unsuitable for ML applications involving sparse data; e.g., recommender systems or genomics. Even in plaintext, such applications involve high-dimensional sparse data, that cannot be processed without sparsity-related optimizations due to prohibitively large memory requirements. Since matrix multiplication is a central building block of ML algorithms, our work proposes dedicated MPC algorithms to multiply secret-shared sparse matrices. Our sparse algorithms have several advantages over secure dense matrix multiplications (i.e., the classic multiplication). On the one hand, they avoid the memory issues caused by the "dense" data representation of dense multiplications. On the other hand, our algorithms can significantly reduce communication costs (up to $\times1000$) for realistic problem sizes. We validate our algorithms in two machine learning applications where dense matrix multiplications are impractical. Finally, we take inspiration from real-world sparse data properties to build 3 techniques minimizing the public knowledge necessary to secure sparse algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14894
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Secure Sparse Matrix Multiplications and their Applications to Privacy-Preserving Machine Learning
Damie, Marc
Hahn, Florian
Peter, Andreas
Ramon, Jan
Cryptography and Security
Machine Learning
To preserve data privacy, multi-party computation (MPC) enables executing Machine Learning (ML) algorithms on private data. However, MPC frameworks do not include optimized operations on sparse data. This absence makes them unsuitable for ML applications involving sparse data; e.g., recommender systems or genomics. Even in plaintext, such applications involve high-dimensional sparse data, that cannot be processed without sparsity-related optimizations due to prohibitively large memory requirements. Since matrix multiplication is a central building block of ML algorithms, our work proposes dedicated MPC algorithms to multiply secret-shared sparse matrices. Our sparse algorithms have several advantages over secure dense matrix multiplications (i.e., the classic multiplication). On the one hand, they avoid the memory issues caused by the "dense" data representation of dense multiplications. On the other hand, our algorithms can significantly reduce communication costs (up to $\times1000$) for realistic problem sizes. We validate our algorithms in two machine learning applications where dense matrix multiplications are impractical. Finally, we take inspiration from real-world sparse data properties to build 3 techniques minimizing the public knowledge necessary to secure sparse algorithms.
title Secure Sparse Matrix Multiplications and their Applications to Privacy-Preserving Machine Learning
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2510.14894