BC-EdgeFL: A Defensive Transmission Model Based on Blockchain-Assisted Reinforced Federated Learning in IIoT Environment

Peiying Zhang; Yanrong Hong; Neeraj Kumar; Mamoun Alazab; Mohammad Dahman Alshehri; Chunxiao Jiang

doi:10.1109/TII.2021.3116037

BC-EdgeFL: A Defensive Transmission Model Based on Blockchain-Assisted Reinforced Federated Learning in IIoT Environment

Peiying Zhang, Yanrong Hong, Neeraj Kumar, Mamoun Alazab, Mohammad Dahman Alshehri, Chunxiao Jiang

Research output: Contribution to journal › Article › peer-review

26 Citations (Scopus)

Abstract

Under the times of the Industrial Internet of Things, the traditional centralized machine learning management method cannot deal with such huge data streams, and the problem of data privacy has aroused widespread concern. In view of these difficulties, in this article, we use the advantages of edge computing and federated learning, combined with the outstanding characteristics of the blockchain, to propose a secure data transmission method. First, we separate the local model updating process from the mobile device independent process; second, we add an edge server so that most of the computation is carried out on the server, which improves the learning efficiency; and finally, we use a distributed architecture of the blockchain to protect data security and privacy. Extensive simulation experiments show that the accuracy of our model can reach 98%. In addition, BC-EdgeFLs interception rate of illegal information can reach 0.8, which has good defensive capabilities. Therefore, the security of data transmission can be strongly guaranteed.

Original language	English
Pages (from-to)	3551-3561
Number of pages	11
Journal	IEEE Transactions on Industrial Informatics
Volume	18
Issue number	5
DOIs	https://doi.org/10.1109/TII.2021.3116037
Publication status	Published - 1 May 2022

Bibliographical note

Funding Information:
The So Cal VOICe also attributes much of its success to its close relationship with the Southern California Vascular Surgery Society (SCVSS). The So Cal VOICe was formed under the auspices of the SCVSS and is supported financially by the society. The medical director of the So Cal VOICe sits on the Board of the SCVSS and is actively involved in any decisions regarding the So Cal VOICe. The spring regional meeting of the So Cal VOICe is held in conjunction with the annual meeting of the SCVSS and all members of the society, whether they are VQI® participants or not, are invited to attend. A segment of the SCVSS program is dedicated annually to an update of the activities of the VQI® and the So Cal VOICe, which encourages SCVSS members who are not VQI® participants to become participants.

Publisher Copyright:
© 2005-2012 IEEE.

Access to Document

10.1109/TII.2021.3116037

Cite this

@article{81a4ce5b7be34bd293bf53721ed1f28e,

title = "BC-EdgeFL: A Defensive Transmission Model Based on Blockchain-Assisted Reinforced Federated Learning in IIoT Environment",

abstract = "Under the times of the Industrial Internet of Things, the traditional centralized machine learning management method cannot deal with such huge data streams, and the problem of data privacy has aroused widespread concern. In view of these difficulties, in this article, we use the advantages of edge computing and federated learning, combined with the outstanding characteristics of the blockchain, to propose a secure data transmission method. First, we separate the local model updating process from the mobile device independent process; second, we add an edge server so that most of the computation is carried out on the server, which improves the learning efficiency; and finally, we use a distributed architecture of the blockchain to protect data security and privacy. Extensive simulation experiments show that the accuracy of our model can reach 98%. In addition, BC-EdgeFLs interception rate of illegal information can reach 0.8, which has good defensive capabilities. Therefore, the security of data transmission can be strongly guaranteed. ",

keywords = "Blockchain, data transmission method, edge computing (EC), federated learning (FL), industrial Internet of Things (IIoT)",

author = "Peiying Zhang and Yanrong Hong and Neeraj Kumar and Mamoun Alazab and Alshehri, {Mohammad Dahman} and Chunxiao Jiang",

note = "Funding Information: The So Cal VOICe also attributes much of its success to its close relationship with the Southern California Vascular Surgery Society (SCVSS). The So Cal VOICe was formed under the auspices of the SCVSS and is supported financially by the society. The medical director of the So Cal VOICe sits on the Board of the SCVSS and is actively involved in any decisions regarding the So Cal VOICe. The spring regional meeting of the So Cal VOICe is held in conjunction with the annual meeting of the SCVSS and all members of the society, whether they are VQI{\textregistered} participants or not, are invited to attend. A segment of the SCVSS program is dedicated annually to an update of the activities of the VQI{\textregistered} and the So Cal VOICe, which encourages SCVSS members who are not VQI{\textregistered} participants to become participants. Publisher Copyright: {\textcopyright} 2005-2012 IEEE.",

year = "2022",

month = may,

day = "1",

doi = "10.1109/TII.2021.3116037",

language = "English",

volume = "18",

pages = "3551--3561",

journal = "IEEE Transactions on Industrial Informatics",

issn = "1551-3203",

publisher = "IEEE Computer Society",

number = "5",

}

TY - JOUR

T1 - BC-EdgeFL

T2 - A Defensive Transmission Model Based on Blockchain-Assisted Reinforced Federated Learning in IIoT Environment

AU - Zhang, Peiying

AU - Hong, Yanrong

AU - Kumar, Neeraj

AU - Alazab, Mamoun

AU - Alshehri, Mohammad Dahman

AU - Jiang, Chunxiao

N1 - Funding Information: The So Cal VOICe also attributes much of its success to its close relationship with the Southern California Vascular Surgery Society (SCVSS). The So Cal VOICe was formed under the auspices of the SCVSS and is supported financially by the society. The medical director of the So Cal VOICe sits on the Board of the SCVSS and is actively involved in any decisions regarding the So Cal VOICe. The spring regional meeting of the So Cal VOICe is held in conjunction with the annual meeting of the SCVSS and all members of the society, whether they are VQI® participants or not, are invited to attend. A segment of the SCVSS program is dedicated annually to an update of the activities of the VQI® and the So Cal VOICe, which encourages SCVSS members who are not VQI® participants to become participants. Publisher Copyright: © 2005-2012 IEEE.

PY - 2022/5/1

Y1 - 2022/5/1

N2 - Under the times of the Industrial Internet of Things, the traditional centralized machine learning management method cannot deal with such huge data streams, and the problem of data privacy has aroused widespread concern. In view of these difficulties, in this article, we use the advantages of edge computing and federated learning, combined with the outstanding characteristics of the blockchain, to propose a secure data transmission method. First, we separate the local model updating process from the mobile device independent process; second, we add an edge server so that most of the computation is carried out on the server, which improves the learning efficiency; and finally, we use a distributed architecture of the blockchain to protect data security and privacy. Extensive simulation experiments show that the accuracy of our model can reach 98%. In addition, BC-EdgeFLs interception rate of illegal information can reach 0.8, which has good defensive capabilities. Therefore, the security of data transmission can be strongly guaranteed.

AB - Under the times of the Industrial Internet of Things, the traditional centralized machine learning management method cannot deal with such huge data streams, and the problem of data privacy has aroused widespread concern. In view of these difficulties, in this article, we use the advantages of edge computing and federated learning, combined with the outstanding characteristics of the blockchain, to propose a secure data transmission method. First, we separate the local model updating process from the mobile device independent process; second, we add an edge server so that most of the computation is carried out on the server, which improves the learning efficiency; and finally, we use a distributed architecture of the blockchain to protect data security and privacy. Extensive simulation experiments show that the accuracy of our model can reach 98%. In addition, BC-EdgeFLs interception rate of illegal information can reach 0.8, which has good defensive capabilities. Therefore, the security of data transmission can be strongly guaranteed.

KW - Blockchain

KW - data transmission method

KW - edge computing (EC)

KW - federated learning (FL)

KW - industrial Internet of Things (IIoT)

UR - http://www.scopus.com/inward/record.url?scp=85124614527&partnerID=8YFLogxK

U2 - 10.1109/TII.2021.3116037

DO - 10.1109/TII.2021.3116037

M3 - Article

AN - SCOPUS:85124614527

SN - 1551-3203

VL - 18

SP - 3551

EP - 3561

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

IS - 5

ER -

BC-EdgeFL: A Defensive Transmission Model Based on Blockchain-Assisted Reinforced Federated Learning in IIoT Environment

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this