GHEFL: Grouping Based on Homomorphic Encryption Validates Federated Learning

Federated learning is a powerful tool for securing participants’ private data due to its ability to make data “available but not visible”. In recent years, federated learning has been enhanced by the emergence of multi-weight aggregation protocols, which minimize the impact of erroneous parameters,...

Full description

Saved in:
Bibliographic Details
Main Authors: Yulin Kang, Wuzheng Tan, Linlin Fan, Yinuo Chen, Xinbin Lai, Jian Weng
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Future Internet
Subjects:
Online Access:https://www.mdpi.com/1999-5903/17/3/128
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850090555935031296
author Yulin Kang
Wuzheng Tan
Linlin Fan
Yinuo Chen
Xinbin Lai
Jian Weng
author_facet Yulin Kang
Wuzheng Tan
Linlin Fan
Yinuo Chen
Xinbin Lai
Jian Weng
author_sort Yulin Kang
collection DOAJ
description Federated learning is a powerful tool for securing participants’ private data due to its ability to make data “available but not visible”. In recent years, federated learning has been enhanced by the emergence of multi-weight aggregation protocols, which minimize the impact of erroneous parameters, and verifiable protocols, which prevent server misbehavior. However, it still faces significant security and performance challenges. Malicious participants may infer the private data of others or carry out poisoning attacks to compromise the model’s correctness. Similarly, malicious servers may return incorrect aggregation results, undermining the model’s convergence. Furthermore, substantial communication overhead caused by interactions between participants or between participants and servers hinders the development of federated learning. In response to this, this paper proposes GHEFL, a group-based, verifiable, federated learning method based on homomorphic encryption that aims to prevent servers from maliciously stealing participant privacy data or performing malicious aggregation. While ensuring the usability of the aggregated model, it strives to minimize the workload on the server as much as possible. Finally, we experimentally evaluate the performance of GHEFL.
format Article
id doaj-art-3981948ec8be4f7e94fcc417191f26c1
institution DOAJ
issn 1999-5903
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Future Internet
spelling doaj-art-3981948ec8be4f7e94fcc417191f26c12025-08-20T02:42:32ZengMDPI AGFuture Internet1999-59032025-03-0117312810.3390/fi17030128GHEFL: Grouping Based on Homomorphic Encryption Validates Federated LearningYulin Kang0Wuzheng Tan1Linlin Fan2Yinuo Chen3Xinbin Lai4Jian Weng5College of Cyber Security, Jinan University, Guangzhou 511436, ChinaCollege of Cyber Security, Jinan University, Guangzhou 511436, ChinaCollege of Cyber Security, Jinan University, Guangzhou 511436, ChinaCollege of Cyber Security, Jinan University, Guangzhou 511436, ChinaCollege of Cyber Security, Jinan University, Guangzhou 511436, ChinaCollege of Cyber Security, Jinan University, Guangzhou 511436, ChinaFederated learning is a powerful tool for securing participants’ private data due to its ability to make data “available but not visible”. In recent years, federated learning has been enhanced by the emergence of multi-weight aggregation protocols, which minimize the impact of erroneous parameters, and verifiable protocols, which prevent server misbehavior. However, it still faces significant security and performance challenges. Malicious participants may infer the private data of others or carry out poisoning attacks to compromise the model’s correctness. Similarly, malicious servers may return incorrect aggregation results, undermining the model’s convergence. Furthermore, substantial communication overhead caused by interactions between participants or between participants and servers hinders the development of federated learning. In response to this, this paper proposes GHEFL, a group-based, verifiable, federated learning method based on homomorphic encryption that aims to prevent servers from maliciously stealing participant privacy data or performing malicious aggregation. While ensuring the usability of the aggregated model, it strives to minimize the workload on the server as much as possible. Finally, we experimentally evaluate the performance of GHEFL.https://www.mdpi.com/1999-5903/17/3/128data privacyfederated learningverifiabilitymulti-servershomomorphic encryption
spellingShingle Yulin Kang
Wuzheng Tan
Linlin Fan
Yinuo Chen
Xinbin Lai
Jian Weng
GHEFL: Grouping Based on Homomorphic Encryption Validates Federated Learning
Future Internet
data privacy
federated learning
verifiability
multi-servers
homomorphic encryption
title GHEFL: Grouping Based on Homomorphic Encryption Validates Federated Learning
title_full GHEFL: Grouping Based on Homomorphic Encryption Validates Federated Learning
title_fullStr GHEFL: Grouping Based on Homomorphic Encryption Validates Federated Learning
title_full_unstemmed GHEFL: Grouping Based on Homomorphic Encryption Validates Federated Learning
title_short GHEFL: Grouping Based on Homomorphic Encryption Validates Federated Learning
title_sort ghefl grouping based on homomorphic encryption validates federated learning
topic data privacy
federated learning
verifiability
multi-servers
homomorphic encryption
url https://www.mdpi.com/1999-5903/17/3/128
work_keys_str_mv AT yulinkang gheflgroupingbasedonhomomorphicencryptionvalidatesfederatedlearning
AT wuzhengtan gheflgroupingbasedonhomomorphicencryptionvalidatesfederatedlearning
AT linlinfan gheflgroupingbasedonhomomorphicencryptionvalidatesfederatedlearning
AT yinuochen gheflgroupingbasedonhomomorphicencryptionvalidatesfederatedlearning
AT xinbinlai gheflgroupingbasedonhomomorphicencryptionvalidatesfederatedlearning
AT jianweng gheflgroupingbasedonhomomorphicencryptionvalidatesfederatedlearning