Verifiable secure aggregation scheme for privacy protection in federated learning networks

Abstract Federated learning enables multiple participants to construct a distributed machine learning system coordinated by a server. Most existing solutions assume a semi-honest system, considering each participant to be honest but curious, which does not align with the complex real-world environme...

Full description

Saved in:
Bibliographic Details
Main Authors: Wujun Yao, Tanping Zhou, Yiliang Han, Xiaolin Wang
Format: Article
Language:English
Published: Springer 2025-08-01
Series:Discover Computing
Subjects:
Online Access:https://doi.org/10.1007/s10791-025-09676-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849225967961112576
author Wujun Yao
Tanping Zhou
Yiliang Han
Xiaolin Wang
author_facet Wujun Yao
Tanping Zhou
Yiliang Han
Xiaolin Wang
author_sort Wujun Yao
collection DOAJ
description Abstract Federated learning enables multiple participants to construct a distributed machine learning system coordinated by a server. Most existing solutions assume a semi-honest system, considering each participant to be honest but curious, which does not align with the complex real-world environment. In reality, servers might act maliciously by tampering with or forging aggregation results, which directly threatens the integrity of global models.. To verify the integrity of server aggregation computations while protecting the privacy of clients, this paper introduces a privacy-preserving verifiable secure aggregation scheme for federated learning networks. Initially, we construct a functional reuse private key ring generation algorithm, enabling clients to encrypt and protect their private gradients using the private key ring. Subsequently, leveraging the discrete logarithm difficulty problem, we devise a commitment protocol where clients commit to their encrypted private gradients. Upon receiving the aggregation result from the server, they collaboratively unlock the commitment, thereby verifying the aggregation result. Security analysis demonstrates that our solution effectively ensures privacy protection. We tested the performance using a Raspberry Pi as an edge computing device. Experimental data reveals that, with 100 clients, our scheme demonstrates that the additional costs for proof generation and verification computations are 39.9% and 34.1% of the existing scheme, respectively, highlighting its lightweight nature.
format Article
id doaj-art-1dffa323e09d405595f792903b14e0ec
institution Kabale University
issn 2948-2992
language English
publishDate 2025-08-01
publisher Springer
record_format Article
series Discover Computing
spelling doaj-art-1dffa323e09d405595f792903b14e0ec2025-08-24T11:46:33ZengSpringerDiscover Computing2948-29922025-08-0128113010.1007/s10791-025-09676-1Verifiable secure aggregation scheme for privacy protection in federated learning networksWujun Yao0Tanping Zhou1Yiliang Han2Xiaolin Wang3College of Cryptography Engineering, Engineering University of People’s Armed PoliceCollege of Cryptography Engineering, Engineering University of People’s Armed PoliceCollege of Cryptography Engineering, Engineering University of People’s Armed PoliceBasic Discipline Department, Engineering University of People’s Armed PoliceAbstract Federated learning enables multiple participants to construct a distributed machine learning system coordinated by a server. Most existing solutions assume a semi-honest system, considering each participant to be honest but curious, which does not align with the complex real-world environment. In reality, servers might act maliciously by tampering with or forging aggregation results, which directly threatens the integrity of global models.. To verify the integrity of server aggregation computations while protecting the privacy of clients, this paper introduces a privacy-preserving verifiable secure aggregation scheme for federated learning networks. Initially, we construct a functional reuse private key ring generation algorithm, enabling clients to encrypt and protect their private gradients using the private key ring. Subsequently, leveraging the discrete logarithm difficulty problem, we devise a commitment protocol where clients commit to their encrypted private gradients. Upon receiving the aggregation result from the server, they collaboratively unlock the commitment, thereby verifying the aggregation result. Security analysis demonstrates that our solution effectively ensures privacy protection. We tested the performance using a Raspberry Pi as an edge computing device. Experimental data reveals that, with 100 clients, our scheme demonstrates that the additional costs for proof generation and verification computations are 39.9% and 34.1% of the existing scheme, respectively, highlighting its lightweight nature.https://doi.org/10.1007/s10791-025-09676-1Federated learningVerifiable aggregationPrivacy protectionEdge computing
spellingShingle Wujun Yao
Tanping Zhou
Yiliang Han
Xiaolin Wang
Verifiable secure aggregation scheme for privacy protection in federated learning networks
Discover Computing
Federated learning
Verifiable aggregation
Privacy protection
Edge computing
title Verifiable secure aggregation scheme for privacy protection in federated learning networks
title_full Verifiable secure aggregation scheme for privacy protection in federated learning networks
title_fullStr Verifiable secure aggregation scheme for privacy protection in federated learning networks
title_full_unstemmed Verifiable secure aggregation scheme for privacy protection in federated learning networks
title_short Verifiable secure aggregation scheme for privacy protection in federated learning networks
title_sort verifiable secure aggregation scheme for privacy protection in federated learning networks
topic Federated learning
Verifiable aggregation
Privacy protection
Edge computing
url https://doi.org/10.1007/s10791-025-09676-1
work_keys_str_mv AT wujunyao verifiablesecureaggregationschemeforprivacyprotectioninfederatedlearningnetworks
AT tanpingzhou verifiablesecureaggregationschemeforprivacyprotectioninfederatedlearningnetworks
AT yilianghan verifiablesecureaggregationschemeforprivacyprotectioninfederatedlearningnetworks
AT xiaolinwang verifiablesecureaggregationschemeforprivacyprotectioninfederatedlearningnetworks