Autoencoder for Detecting Malicious Updates in Differentially Private Federated Learning

Lucia Alonso, Mina Alishahi

2024

Abstract

Differentially Private Federated Learning (DP-FL) is a novel machine learning paradigm that integrates federated learning with the principles of differential privacy. In DP-FL, a global model is trained across decentralized devices or servers, each holding local data samples, without the need to exchange raw data. This approach ensures data privacy by adding noise to the model updates before aggregation, thus preventing any individual contributor’s data from being compromised. However, ensuring the integrity of the model updates from these contributors is paramount. This research explores the application of autoencoders as a means to detect anomalous or fraudulent updates from contributors in DP-FL. By leveraging the reconstruction errors generated by autoencoders, this study assesses their effectiveness in identifying anomalies while also discussing potential limitations of this approach.

Paper Citation

in Harvard Style

Alonso L. and Alishahi M. (2024). Autoencoder for Detecting Malicious Updates in Differentially Private Federated Learning. In Proceedings of the 21st International Conference on Security and Cryptography - Volume 1: SECRYPT; ISBN 978-989-758-709-2, SciTePress, pages 467-474. DOI: 10.5220/0012766700003767

in Bibtex Style

@conference{secrypt24,
author={Lucia Alonso and Mina Alishahi},
title={Autoencoder for Detecting Malicious Updates in Differentially Private Federated Learning},
booktitle={Proceedings of the 21st International Conference on Security and Cryptography - Volume 1: SECRYPT},
year={2024},
pages={467-474},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012766700003767},
isbn={978-989-758-709-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 21st International Conference on Security and Cryptography - Volume 1: SECRYPT
TI - Autoencoder for Detecting Malicious Updates in Differentially Private Federated Learning
SN - 978-989-758-709-2
AU - Alonso L.
AU - Alishahi M.
PY - 2024
SP - 467
EP - 474
DO - 10.5220/0012766700003767
PB - SciTePress