FedTwin: Blockchain-Enabled Adaptive Asynchronous Federated Learning for Digital Twin Networks

Qu, Y; Gao, L; Xiang, Y; Shen, S; Yu, S

FedTwin: Blockchain-Enabled Adaptive Asynchronous Federated Learning for Digital Twin Networks

Qu, Y Gao, L Xiang, Y Shen, S Yu, S

Permalink

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)
Publication Type:: Journal Article
Citation:: IEEE Network, 2022, 36, (6), pp. 183-190
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	Network_Magazine_2021 v2.pdf	Submitted version	260.21 kB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Qu, Y
dc.contributor.author	Gao, L
dc.contributor.author	Xiang, Y
dc.contributor.author	Shen, S
dc.contributor.author	Yu, S https://orcid.org/0000-0003-4485-6743
dc.date.accessioned	2023-01-25T02:24:30Z
dc.date.available	2023-01-25T02:24:30Z
dc.date.issued	2022-01-01
dc.identifier.citation	IEEE Network, 2022, 36, (6), pp. 183-190
dc.identifier.issn	0890-8044
dc.identifier.issn	1558-156X
dc.identifier.uri	http://hdl.handle.net/10453/165422
dc.description.abstract	The fast proliferation of digital twin (DT) establishes a direct connection between the physical entity and its deployed digital representation. As markets shift toward mass customization and new service delivery models, the digital representation has become more adaptive and agile by forming digital twin networks (DTN). DTN institutes a real-time single source of truth everywhere. However, there are several issues preventing DTN from further application, which are centralized processing, data falsification, privacy leakage, lack of incentive mechanism, etc. To make DTN better meet the ever-changing demands, we propose a novel blockchain-enabled adaptive asynchronous federated learning (FedTwin) paradigm for privacy-preserving and decentralized DTN. We design Proof-of-Federalism (PoF), which is a tailor-made consensus algorithm for autonomous DTN. In each DT's local training phase, generative adversarial network enhanced differential privacy is used to protect the privacy of local model parameters while a modified Isolation Forest is deployed to filter out the falsified DTs. In the global aggregation phase, an improved Markov decision process is leveraged to select optimal DTs to achieve adaptive asynchronous aggregation while providing a roll-back mechanism to redact the falsified global models. With this paper, we aim to provide insights to the forthcoming researchers and readers in this under-explored domain.
dc.language	en
dc.publisher	Institute of Electrical and Electronics Engineers (IEEE)
dc.relation	http://purl.org/au-research/grants/arc/LP190100676
dc.relation	http://purl.org/au-research/grants/arc/DP200101374
dc.relation.ispartof	IEEE Network
dc.relation.isbasedon	10.1109/MNET.105.2100620
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0805 Distributed Computing, 0906 Electrical and Electronic Engineering
dc.subject.classification	Networking & Telecommunications
dc.title	FedTwin: Blockchain-Enabled Adaptive Asynchronous Federated Learning for Digital Twin Networks
dc.type	Journal Article
utslib.citation.volume	36
utslib.for	0805 Distributed Computing
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2023-01-25T02:24:28Z
pubs.issue	6
pubs.publication-status	Published
pubs.volume	36
utslib.citation.issue	6

Abstract:

The fast proliferation of digital twin (DT) establishes a direct connection between the physical entity and its deployed digital representation. As markets shift toward mass customization and new service delivery models, the digital representation has become more adaptive and agile by forming digital twin networks (DTN). DTN institutes a real-time single source of truth everywhere. However, there are several issues preventing DTN from further application, which are centralized processing, data falsification, privacy leakage, lack of incentive mechanism, etc. To make DTN better meet the ever-changing demands, we propose a novel blockchain-enabled adaptive asynchronous federated learning (FedTwin) paradigm for privacy-preserving and decentralized DTN. We design Proof-of-Federalism (PoF), which is a tailor-made consensus algorithm for autonomous DTN. In each DT's local training phase, generative adversarial network enhanced differential privacy is used to protect the privacy of local model parameters while a modified Isolation Forest is deployed to filter out the falsified DTs. In the global aggregation phase, an improved Markov decision process is leveraged to select optimal DTs to achieve adaptive asynchronous aggregation while providing a roll-back mechanism to redact the falsified global models. With this paper, we aim to provide insights to the forthcoming researchers and readers in this under-explored domain.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/165422