Machine Learning for All: A More Robust Federated Learning Framework

Chamatidis Ilias, Spathoulas Georgios

2019

Abstract

Machine learning and especially deep learning are appropriate for solving multiple problems in various domains. Training such models though, demands significant processing power and requires large data-sets. Federated learning is an approach that merely solves these problems, as multiple users constitute a distributed network and each one of them trains a model locally with his data. This network can cumulatively sum up significant processing power to conduct training efficiently, while it is easier to preserve privacy, as data does not leave its owner. Nevertheless, it has been proven that federated learning also faces privacy and integrity issues. In this paper a general enhanced federated learning framework is presented. Users may provide data or the required processing power or participate just in order to train their models. Homomorphic encryption algorithms are employed to enable model training on encrypted data. Blockchain technology is used as smart contracts coordinate the work-flow and the commitments made between all participating nodes, while at the same time, tokens exchanges between nodes provide the required incentives for users to participate in the scheme and to act legitimately.

Paper Citation

in Harvard Style

Ilias C. and Georgios S. (2019). Machine Learning for All: A More Robust Federated Learning Framework.In Proceedings of the 5th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP, ISBN 978-989-758-359-9, pages 544-551. DOI: 10.5220/0007571705440551

in Bibtex Style

@conference{icissp19,
author={Chamatidis Ilias and Spathoulas Georgios},
title={Machine Learning for All: A More Robust Federated Learning Framework},
booktitle={Proceedings of the 5th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,},
year={2019},
pages={544-551},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007571705440551},
isbn={978-989-758-359-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 5th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,
TI - Machine Learning for All: A More Robust Federated Learning Framework
SN - 978-989-758-359-9
AU - Ilias C.
AU - Georgios S.
PY - 2019
SP - 544
EP - 551
DO - 10.5220/0007571705440551