Low-Latency Privacy-Preserving Deep Learning Design via Secure MPC

TL;DR

This paper introduces a low-latency, privacy-preserving deep learning method using secure MPC that reduces communication overhead and enhances computation efficiency, achieving significant speedups in secure neural network training.

Contribution

It proposes a novel secret-sharing-based MPC design with reduced communication rounds and improved nonlinear function computation for faster privacy-preserving deep learning.

Findings

Achieves 10-20% reduction in communication latency.

Effectively improves nonlinear function computation in MPC.

Demonstrates practical speedups in secure deep learning tasks.

Abstract

Secure multi-party computation (MPC) facilitates privacy-preserving computation between multiple parties without leaking private information. While most secure deep learning techniques utilize MPC operations to achieve feasible privacy-preserving machine learning on downstream tasks, the overhead of the computation and communication still hampers their practical application. This work proposes a low-latency secret-sharing-based MPC design that reduces unnecessary communication rounds during the execution of MPC protocols. We also present a method for improving the computation of commonly used nonlinear functions in deep learning by integrating multivariate multiplication and coalescing different packets into one to maximize network utilization. Our experimental results indicate that our method is effective in a variety of settings, with a speedup in communication latency of $10\sim20\%$.