Privacy-enhanced federated learning scheme based on generative adversarial networks

Federated learning, a distributed machine learning paradigm, has gained a lot of attention due to its inherent privacy protection capability and heterogeneous collaboration.However, recent studies have revealed a potential privacy risk known as “gradient leakage”, where the gradients can be used to...

Full description

Saved in:
Bibliographic Details
Main Authors: Feng YU, Qingxin LIN, Hui LIN, Xiaoding WANG
Format: Article
Language:English
Published: POSTS&TELECOM PRESS Co., LTD 2023-06-01
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.2023043
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850092162583101440
author Feng YU
Qingxin LIN
Hui LIN
Xiaoding WANG
author_facet Feng YU
Qingxin LIN
Hui LIN
Xiaoding WANG
author_sort Feng YU
collection DOAJ
description Federated learning, a distributed machine learning paradigm, has gained a lot of attention due to its inherent privacy protection capability and heterogeneous collaboration.However, recent studies have revealed a potential privacy risk known as “gradient leakage”, where the gradients can be used to determine whether a data record with a specific property is included in another participant’s batch, thereby exposing the participant’s training data.Current privacy-enhanced federated learning methods may have drawbacks such as reduced accuracy, computational overhead, or new insecurity factors.To address this issue, a differential privacy-enhanced generative adversarial network model was proposed, which introduced an identifier into vanilla GAN, thus enabling the input data to be approached while satisfying differential privacy constraints.Then this model was applied to the federated learning framework, to improve the privacy protection capability without compromising model accuracy.The proposed method was verified through simulations under the client/server (C/S) federated learning architecture and was found to balance data privacy and practicality effectively compared with the DP-SGD method.Besides, the usability of the proposed model was theoretically analyzed under a peer-to-peer (P2P) architecture, and future research work was discussed.
format Article
id doaj-art-bded461d375a479aa03cc9d379a9db3c
institution DOAJ
issn 2096-109X
language English
publishDate 2023-06-01
publisher POSTS&TELECOM PRESS Co., LTD
record_format Article
series 网络与信息安全学报
spelling doaj-art-bded461d375a479aa03cc9d379a9db3c2025-08-20T02:42:11ZengPOSTS&TELECOM PRESS Co., LTD网络与信息安全学报2096-109X2023-06-01911312259578484Privacy-enhanced federated learning scheme based on generative adversarial networksFeng YUQingxin LINHui LINXiaoding WANGFederated learning, a distributed machine learning paradigm, has gained a lot of attention due to its inherent privacy protection capability and heterogeneous collaboration.However, recent studies have revealed a potential privacy risk known as “gradient leakage”, where the gradients can be used to determine whether a data record with a specific property is included in another participant’s batch, thereby exposing the participant’s training data.Current privacy-enhanced federated learning methods may have drawbacks such as reduced accuracy, computational overhead, or new insecurity factors.To address this issue, a differential privacy-enhanced generative adversarial network model was proposed, which introduced an identifier into vanilla GAN, thus enabling the input data to be approached while satisfying differential privacy constraints.Then this model was applied to the federated learning framework, to improve the privacy protection capability without compromising model accuracy.The proposed method was verified through simulations under the client/server (C/S) federated learning architecture and was found to balance data privacy and practicality effectively compared with the DP-SGD method.Besides, the usability of the proposed model was theoretically analyzed under a peer-to-peer (P2P) architecture, and future research work was discussed.http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2023043federated learninggradient leakageprivacy enhancementgenerative adversarial networkdifferential privacy
spellingShingle Feng YU
Qingxin LIN
Hui LIN
Xiaoding WANG
Privacy-enhanced federated learning scheme based on generative adversarial networks
网络与信息安全学报
federated learning
gradient leakage
privacy enhancement
generative adversarial network
differential privacy
title Privacy-enhanced federated learning scheme based on generative adversarial networks
title_full Privacy-enhanced federated learning scheme based on generative adversarial networks
title_fullStr Privacy-enhanced federated learning scheme based on generative adversarial networks
title_full_unstemmed Privacy-enhanced federated learning scheme based on generative adversarial networks
title_short Privacy-enhanced federated learning scheme based on generative adversarial networks
title_sort privacy enhanced federated learning scheme based on generative adversarial networks
topic federated learning
gradient leakage
privacy enhancement
generative adversarial network
differential privacy
url http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2023043
work_keys_str_mv AT fengyu privacyenhancedfederatedlearningschemebasedongenerativeadversarialnetworks
AT qingxinlin privacyenhancedfederatedlearningschemebasedongenerativeadversarialnetworks
AT huilin privacyenhancedfederatedlearningschemebasedongenerativeadversarialnetworks
AT xiaodingwang privacyenhancedfederatedlearningschemebasedongenerativeadversarialnetworks