Federated Learning with Differential Privacy and an Untrusted Aggregator

Kunlong Liu, Trinabh Gupta

2024

Abstract

Federated learning for training models over mobile devices is gaining popularity. Current systems for this task exhibit significant trade-offs between model accuracy, privacy guarantee, and device efficiency. For instance, Oort (OSDI 2021) provides excellent accuracy and efficiency but requires a trusted central server. On the other hand, Orchard (OSDI 2020) provides good accuracy and the differential privacy guarantee without a trusted server, but creates high overhead for the devices. This paper describes Aero, a new federated learning system that significantly improves this trade-off. Aero guarantees good accuracy, differential privacy without a trusted server, and low device overhead. The key idea of Aero is to tune system architecture and design to a specific federated learning algorithm. This tuning requires novel optimizations and techniques, including a new protocol to securely aggregate gradient updates from devices. An evaluation of Aero demonstrates that it provides comparable accuracy to plain federated learning (without differential privacy), and it improves efficiency ( CPU and network) over Orchard by a factor of 10 5 .

Paper Citation

in Harvard Style

Liu K. and Gupta T. (2024). Federated Learning with Differential Privacy and an Untrusted Aggregator. In Proceedings of the 10th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP; ISBN 978-989-758-683-5, SciTePress, pages 379-389. DOI: 10.5220/0012322100003648

in Bibtex Style

@conference{icissp24,
author={Kunlong Liu and Trinabh Gupta},
title={Federated Learning with Differential Privacy and an Untrusted Aggregator},
booktitle={Proceedings of the 10th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP},
year={2024},
pages={379-389},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012322100003648},
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 - Federated Learning with Differential Privacy and an Untrusted Aggregator
SN - 978-989-758-683-5
AU - Liu K.
AU - Gupta T.
PY - 2024
SP - 379
EP - 389
DO - 10.5220/0012322100003648
PB - SciTePress