Robust and Verifiable MPC with Applications to Linear Machine Learning Inference

TL;DR

This paper introduces a secure multi-party computation protocol that ensures strong security, identifiability, and robustness, enabling reliable linear machine learning inference with improved security guarantees over existing methods.

Contribution

We develop a robust, verifiable MPC protocol with complete identifiability and robustness, addressing efficiency issues in prior schemes and applying it to secure linear machine learning inference.

Findings

Achieved robustness with a semi-honest trusted third party.

Benchmarked the protocol showing efficient recovery from malicious behavior.

Demonstrated application to ML inference with competitive performance.

Abstract

In this work, we present an efficient secure multi-party computation MPC protocol that provides strong security guarantees in settings with dishonest majority of participants who may behave arbitrarily. Unlike the popular MPC implementation known as SPDZ [Crypto '12], which only ensures security with abort, our protocol achieves both complete identifiability and robustness. With complete identifiability, honest parties can detect and unanimously agree on the identity of any malicious party. Robustness allows the protocol to continue with the computation without requiring a restart, even when malicious behavior is detected. Additionally, our approach addresses the performance limitations observed in the protocol by Cunningham et al. [ICITS '17], which, while achieving complete identifiability, is hindered by the costly exponentiation operations required by the choice of commitment scheme. Our protocol is based on the approach by Rivinius et al. [S&P '22], utilizing lattice-based commitment for better efficiency. We achieved robustness with the help of a semi-honest trusted third party. We benchmark our robust protocol, showing the efficient recovery from parties' malicious behavior. Finally, we benchmark our protocol on a ML-as-a-service scenario, wherein clients off-load the desired computation to the servers, and verify the computation result. We benchmark on linear ML inference, running on various datasets. While our efficiency is slightly lower compared to SPDZ's, we offer stronger security properties that provide distinct advantages.