BalancedSecAgg: Toward Fast Secure Aggregation for Federated Learning

Federated learning is a promising collaborative learning system from the perspective of training data privacy preservation; however, there is a risk of privacy leakage from individual local models of users. Secure aggregation protocols based on local model masking are a promising solution to prevent...

Full description

Saved in:
Bibliographic Details
Main Authors: Hiroki Masuda, Kentaro Kita, Yuki Koizumi, Junji Takemasa, Toru Hasegawa
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10744018/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846163829217558528
author Hiroki Masuda
Kentaro Kita
Yuki Koizumi
Junji Takemasa
Toru Hasegawa
author_facet Hiroki Masuda
Kentaro Kita
Yuki Koizumi
Junji Takemasa
Toru Hasegawa
author_sort Hiroki Masuda
collection DOAJ
description Federated learning is a promising collaborative learning system from the perspective of training data privacy preservation; however, there is a risk of privacy leakage from individual local models of users. Secure aggregation protocols based on local model masking are a promising solution to prevent privacy leakage. Existing secure aggregation protocols sacrifice either computation or communication costs to tolerate user dropouts. A naive secure aggregation protocol achieves a small communication cost by secretly sharing random seeds instead of random masks. However, it requires that a server incurs a substantial computation cost to reconstruct the random masks from the random seeds of dropout users. To avoid such a reconstruction, a state-of-the-art secure aggregation protocol secretly shares random masks. Although this approach avoids the computation cost of mask reconstruction, it incurs a large communication cost due to secretly sharing random masks. In this paper, we design a secure aggregation protocol to mitigate the tradeoff between the computation cost and the communication cost by complementing both types of secure aggregation protocols. In our experiments, our protocol achieves up to 11.41 times faster while achieving the same level of privacy preservation and dropout tolerance as the existing protocols.
format Article
id doaj-art-42bf46fec4344a0489e4c31795bb6d1e
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-42bf46fec4344a0489e4c31795bb6d1e2024-11-19T00:02:36ZengIEEEIEEE Access2169-35362024-01-011216526516527910.1109/ACCESS.2024.349177910744018BalancedSecAgg: Toward Fast Secure Aggregation for Federated LearningHiroki Masuda0https://orcid.org/0009-0002-3948-3671Kentaro Kita1https://orcid.org/0000-0002-7982-3530Yuki Koizumi2https://orcid.org/0000-0002-9254-6558Junji Takemasa3https://orcid.org/0000-0002-5361-1855Toru Hasegawa4https://orcid.org/0000-0002-8925-1732Graduate School of Information Science and Technology, Osaka University, Osaka, JapanGraduate School of Information Science and Technology, Osaka University, Osaka, JapanGraduate School of Information Science and Technology, Osaka University, Osaka, JapanGraduate School of Information Science and Technology, Osaka University, Osaka, JapanFaculty of Materials for Energy, Shimane University, Matsue, Shimane, JapanFederated learning is a promising collaborative learning system from the perspective of training data privacy preservation; however, there is a risk of privacy leakage from individual local models of users. Secure aggregation protocols based on local model masking are a promising solution to prevent privacy leakage. Existing secure aggregation protocols sacrifice either computation or communication costs to tolerate user dropouts. A naive secure aggregation protocol achieves a small communication cost by secretly sharing random seeds instead of random masks. However, it requires that a server incurs a substantial computation cost to reconstruct the random masks from the random seeds of dropout users. To avoid such a reconstruction, a state-of-the-art secure aggregation protocol secretly shares random masks. Although this approach avoids the computation cost of mask reconstruction, it incurs a large communication cost due to secretly sharing random masks. In this paper, we design a secure aggregation protocol to mitigate the tradeoff between the computation cost and the communication cost by complementing both types of secure aggregation protocols. In our experiments, our protocol achieves up to 11.41 times faster while achieving the same level of privacy preservation and dropout tolerance as the existing protocols.https://ieeexplore.ieee.org/document/10744018/Dropout tolerancefederated learningprivacy preservationsecure aggregation
spellingShingle Hiroki Masuda
Kentaro Kita
Yuki Koizumi
Junji Takemasa
Toru Hasegawa
BalancedSecAgg: Toward Fast Secure Aggregation for Federated Learning
IEEE Access
Dropout tolerance
federated learning
privacy preservation
secure aggregation
title BalancedSecAgg: Toward Fast Secure Aggregation for Federated Learning
title_full BalancedSecAgg: Toward Fast Secure Aggregation for Federated Learning
title_fullStr BalancedSecAgg: Toward Fast Secure Aggregation for Federated Learning
title_full_unstemmed BalancedSecAgg: Toward Fast Secure Aggregation for Federated Learning
title_short BalancedSecAgg: Toward Fast Secure Aggregation for Federated Learning
title_sort balancedsecagg toward fast secure aggregation for federated learning
topic Dropout tolerance
federated learning
privacy preservation
secure aggregation
url https://ieeexplore.ieee.org/document/10744018/
work_keys_str_mv AT hirokimasuda balancedsecaggtowardfastsecureaggregationforfederatedlearning
AT kentarokita balancedsecaggtowardfastsecureaggregationforfederatedlearning
AT yukikoizumi balancedsecaggtowardfastsecureaggregationforfederatedlearning
AT junjitakemasa balancedsecaggtowardfastsecureaggregationforfederatedlearning
AT toruhasegawa balancedsecaggtowardfastsecureaggregationforfederatedlearning