Paper 2025/786

Robust and Verifiable MPC with Applications to Linear Machine Learning Inference

Tzu-Shen Wang, Texas A&M University
Jimmy Dani, Texas A&M University
Juan Garay, Texas A&M University
Soamar Homsi, Air Force Research Laboratory
Nitesh Saxena, Texas A&M University
Abstract

In this work, we present an efficient secure multi-party computation MPC protocol that provides strong security guarantees in settings with a 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 achieves 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.

Metadata
Available format(s)
PDF
Category
Cryptographic protocols
Publication info
Preprint.
Keywords
Multi-Party ComputationRobustnessMachine Learning
Contact author(s)
jasonwang017 @ tamu edu
danijy @ tamu edu
garay @ tamu edu
soamar homsi @ us af mil
nsaxena @ tamu edu
History
2025-05-04: approved
2025-05-02: received
See all versions
Short URL
https://ia.cr/2025/786
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2025/786,
      author = {Tzu-Shen Wang and Jimmy Dani and Juan Garay and Soamar Homsi and Nitesh Saxena},
      title = {Robust and Verifiable {MPC} with Applications to Linear Machine Learning Inference},
      howpublished = {Cryptology {ePrint} Archive, Paper 2025/786},
      year = {2025},
      url = {https://eprint.iacr.org/2025/786}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.