Saved in:
Bibliographic Details
Main Authors: Tao, Tianle, Peng, Shizhao, Zhu, Haogang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.06104
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914143861211136
author Tao, Tianle
Peng, Shizhao
Zhu, Haogang
author_facet Tao, Tianle
Peng, Shizhao
Zhu, Haogang
contents Efficiency and communication cost remain critical bottlenecks for practical Privacy-Preserving Machine Learning (PPML). Most existing frameworks rely on fixed-point arithmetic for strong security, which introduces significant precision loss and requires expensive cross-domain conversions (e.g., Arithmetic-to-Boolean) for non-linear operations. To address this, we propose PraxiMLP, a highly efficient three-party MLP framework grounded in practical security. The core of our work is a pair of novel additive-to-multiplicative conversion protocols that operate entirely within the arithmetic domain, thus avoiding expensive cross-domain conversions. By natively supporting loating-point numbers, PraxiMLP precisely handles non-linear functions, dramatically improving both efficiency and precision. Experimental results confirm that, compared to mainstream PPML frameworks, PraxiMLP delivers an average 8 orders of magnitude precision improvement on basic protocols and a 5x average model training speedup in a WAN environment.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06104
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PraxiMLP: A Threshold-based Framework for Efficient Three-Party MLP with Practical Security
Tao, Tianle
Peng, Shizhao
Zhu, Haogang
Cryptography and Security
Efficiency and communication cost remain critical bottlenecks for practical Privacy-Preserving Machine Learning (PPML). Most existing frameworks rely on fixed-point arithmetic for strong security, which introduces significant precision loss and requires expensive cross-domain conversions (e.g., Arithmetic-to-Boolean) for non-linear operations. To address this, we propose PraxiMLP, a highly efficient three-party MLP framework grounded in practical security. The core of our work is a pair of novel additive-to-multiplicative conversion protocols that operate entirely within the arithmetic domain, thus avoiding expensive cross-domain conversions. By natively supporting loating-point numbers, PraxiMLP precisely handles non-linear functions, dramatically improving both efficiency and precision. Experimental results confirm that, compared to mainstream PPML frameworks, PraxiMLP delivers an average 8 orders of magnitude precision improvement on basic protocols and a 5x average model training speedup in a WAN environment.
title PraxiMLP: A Threshold-based Framework for Efficient Three-Party MLP with Practical Security
topic Cryptography and Security
url https://arxiv.org/abs/2511.06104