A Parallel Privacy-Preserving Shortest Path Protocol from a Path Algebra Problem

TL;DR

This paper introduces a secure multiparty computation protocol for shortest path problems in graphs with private edge lengths, leveraging graph separator trees and parallelism to improve efficiency over classical methods.

Contribution

It presents a novel parallel SSSD protocol using path algebra within the SMC framework, optimized for graphs with small separators like planar graphs.

Findings

The protocol achieves better time complexity and parallelism than classical SSSD algorithms.

Implementation on Sharemind MPC demonstrates practical efficiency and scalability.

Benchmarking shows competitive performance against privacy-preserving Bellman-Ford algorithms.

Abstract

In this paper, we present a secure multiparty computation (SMC) protocol for single-source shortest distances (SSSD) in undirected graphs, where the location of edges is public, but their length is private. The protocol works in the Arithmetic Black Box (ABB) model on top of the separator tree of the graph, achieving good time complexity if the subgraphs of the graph have small separators (which is the case for e.g. planar graphs); the achievable parallelism is significantly higher than that of classical SSSD algorithms implemented on top of an ABB. We implement our protocol on top of the Sharemind MPC platform, and perform extensive benchmarking over different network environments. We compare our algorithm against the baseline picked from classical algorithms - privacy-preserving Bellman-Ford algorithm (with public edges).