Federated learning scheme for mobile network based on reputation evaluation mechanism and blockchain

Federated learning is a new distributed machine learning technology, where training tasks are deployed on user side and training model parameters are sent to the server side.In the whole process, participants do not need to share their own data directly, which greatly avoids privacy issues.However,...

Full description

Saved in:
Bibliographic Details
Main Authors: Ming YANG, Xuexian HU, Qihui ZHANG, Jianghong WEI, Wenfen LIU
Format: Article
Language:English
Published: POSTS&TELECOM PRESS Co., LTD 2021-12-01
Series:网络与信息安全学报
Subjects:
Online Access:http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021083
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850091316307820544
author Ming YANG
Xuexian HU
Qihui ZHANG
Jianghong WEI
Wenfen LIU
author_facet Ming YANG
Xuexian HU
Qihui ZHANG
Jianghong WEI
Wenfen LIU
author_sort Ming YANG
collection DOAJ
description Federated learning is a new distributed machine learning technology, where training tasks are deployed on user side and training model parameters are sent to the server side.In the whole process, participants do not need to share their own data directly, which greatly avoids privacy issues.However, the trust relationship between mobile users in the learning model has not been established in advance, there is hidden safety when users perform cooperative train with each other.In view of the above problems, a federated learning scheme for mobile network based on reputation evaluation mechanism and blockchain was proposed.The scheme allowed the server side to use subjective logic models to evaluate the reputation of participating mobile users and provided them with credible reputation opinions sharing environment and dynamic access strategy interface based on the technique of smart contract of blockchain.Theoretical and experimental analys is results show that the scheme can enable the server side to select reliable users for training.And it can achieve more fair and effective reputation calculations, which improves the accuracy of federated learning.
format Article
id doaj-art-c5e774e52c374e328aef93c96dbe702f
institution DOAJ
issn 2096-109X
language English
publishDate 2021-12-01
publisher POSTS&TELECOM PRESS Co., LTD
record_format Article
series 网络与信息安全学报
spelling doaj-art-c5e774e52c374e328aef93c96dbe702f2025-08-20T02:42:24ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2021-12-0179911259569799Federated learning scheme for mobile network based on reputation evaluation mechanism and blockchainMing YANGXuexian HUQihui ZHANGJianghong WEIWenfen LIUFederated learning is a new distributed machine learning technology, where training tasks are deployed on user side and training model parameters are sent to the server side.In the whole process, participants do not need to share their own data directly, which greatly avoids privacy issues.However, the trust relationship between mobile users in the learning model has not been established in advance, there is hidden safety when users perform cooperative train with each other.In view of the above problems, a federated learning scheme for mobile network based on reputation evaluation mechanism and blockchain was proposed.The scheme allowed the server side to use subjective logic models to evaluate the reputation of participating mobile users and provided them with credible reputation opinions sharing environment and dynamic access strategy interface based on the technique of smart contract of blockchain.Theoretical and experimental analys is results show that the scheme can enable the server side to select reliable users for training.And it can achieve more fair and effective reputation calculations, which improves the accuracy of federated learning.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021083mobile networkfederated learningblockchainreputation management
spellingShingle Ming YANG
Xuexian HU
Qihui ZHANG
Jianghong WEI
Wenfen LIU
Federated learning scheme for mobile network based on reputation evaluation mechanism and blockchain
网络与信息安全学报
mobile network
federated learning
blockchain
reputation management
title Federated learning scheme for mobile network based on reputation evaluation mechanism and blockchain
title_full Federated learning scheme for mobile network based on reputation evaluation mechanism and blockchain
title_fullStr Federated learning scheme for mobile network based on reputation evaluation mechanism and blockchain
title_full_unstemmed Federated learning scheme for mobile network based on reputation evaluation mechanism and blockchain
title_short Federated learning scheme for mobile network based on reputation evaluation mechanism and blockchain
title_sort federated learning scheme for mobile network based on reputation evaluation mechanism and blockchain
topic mobile network
federated learning
blockchain
reputation management
url http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2021083
work_keys_str_mv AT mingyang federatedlearningschemeformobilenetworkbasedonreputationevaluationmechanismandblockchain
AT xuexianhu federatedlearningschemeformobilenetworkbasedonreputationevaluationmechanismandblockchain
AT qihuizhang federatedlearningschemeformobilenetworkbasedonreputationevaluationmechanismandblockchain
AT jianghongwei federatedlearningschemeformobilenetworkbasedonreputationevaluationmechanismandblockchain
AT wenfenliu federatedlearningschemeformobilenetworkbasedonreputationevaluationmechanismandblockchain