Outsourcing Privacy-Preserving Federated Learning on Malicious Networks through MPC

Richard Hernandez, Oscar G. Bautista, Mohammad Hossein Manshaei, Abdulhadi Sahin, Kemal Akkaya

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations


While Federated Learning (FL) enables training by only sharing model updates rather than data, FL can still be prone to privacy leaks. Therefore, many efforts have been made to adopt homomorphic encryption or differential privacy approaches to prevent this. However, these solutions come with several issues that may limit their widespread adoption in applications that involve sensitive data sitting in silos. Such issues include but are not limited to trust in the aggregation server, the accuracy of the model, potential collusion among clients, and limited aggregation function support. To address these issues, we advocate using secure Multiparty Computation (MPC) to offer privacy-preserving computation. Specifically, we propose an FL framework that enables outsourcing the model aggregation to MPC parties on untrusted cloud environments and offers correctness verification to the model owners. Unlike differential privacy-based solutions, the proposed framework offers the same level of accuracy as models that are trained on the clear and minimize the possibility of collusion among clients and MPC parties. We implemented and evaluated the proposed framework under various conditions. The results showed that our framework can match the accuracy of centralized FL training while maintaining the required level of privacy and security in malicious cross-silo settings.

Original languageEnglish (US)
Title of host publicationProceedings of the 48th IEEE Conference on Local Computer Networks , LCN 2023
EditorsEyuphan Bulut, Florian Tschorsch, Kanchana Thilakarathna
PublisherIEEE Computer Society
ISBN (Electronic)9798350300734
StatePublished - 2023
Externally publishedYes
Event48th IEEE Conference on Local Computer Networks , LCN 2023 - Daytona Beach, United States
Duration: Oct 2 2023Oct 5 2023

Publication series

NameProceedings - Conference on Local Computer Networks, LCN


Conference48th IEEE Conference on Local Computer Networks , LCN 2023
Country/TerritoryUnited States
CityDaytona Beach


  • Federated Learning
  • Machine Learning
  • Malicious Network
  • Multiparty Computation

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture


Dive into the research topics of 'Outsourcing Privacy-Preserving Federated Learning on Malicious Networks through MPC'. Together they form a unique fingerprint.

Cite this