A Decentralized Federated Learning Using Reputation

Olive Chakraborty, Aymen Boudguiga

2024

Abstract

Nowadays Federated learning (FL) is established as one of the best techniques for collaborative machine learning. It allows a set of clients to train a common model without disclosing their sensitive and private dataset to a coordination server. The latter is in charge of the model aggregation. However, FL faces some problems, regarding the security of updates, integrity of computation and the availability of a server. In this paper, we combine some new ideas like clients’ reputation with techniques like secure aggregation using Homomorphic Encryption and verifiable secret sharing using Multi-Party Computation techniques to design a decentralized FL system that addresses the issues of incentives, security and availability amongst others. One of the original contributions of this work is the new leader election protocol which uses a secure shuffling and is based on a proof of reputation. Indeed, we propose to select an aggregator among the clients participating to the FL training using their reputations. That is, we estimate the reputation of each client at every FL iteration and then we select the next round aggregator from the set of clients with the best reputations. As such, we remove misbehaving clients (e.g., byzantines) from the list of clients eligible for the role of aggregation server.

Paper Citation

in Harvard Style

Chakraborty O. and Boudguiga A. (2024). A Decentralized Federated Learning Using Reputation. In Proceedings of the 10th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP; ISBN 978-989-758-683-5, SciTePress, pages 799-806. DOI: 10.5220/0012428300003648

in Bibtex Style

@conference{icissp24,
author={Olive Chakraborty and Aymen Boudguiga},
title={A Decentralized Federated Learning Using Reputation},
booktitle={Proceedings of the 10th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP},
year={2024},
pages={799-806},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012428300003648},
isbn={978-989-758-683-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP
TI - A Decentralized Federated Learning Using Reputation
SN - 978-989-758-683-5
AU - Chakraborty O.
AU - Boudguiga A.
PY - 2024
SP - 799
EP - 806
DO - 10.5220/0012428300003648
PB - SciTePress