A Novel Blockchain-Enabled Federated Learning Scheme for IoT Anomaly Detection

In this research, we proposed a novel anomaly detection system (ADS) that integrates federated learning (FL) with blockchain for resource-constrained IoT. The proposed system allows IoT devices to exchange machine learning (ML) models through a permissioned blockchain, enabling trustworthy collabora...

Full description

Saved in:
Bibliographic Details
Main Authors: Van-Doan Nguyen, Abebe Diro, Naveen Chilamkurti, Will Heyne, Khoa Tran Phan
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Transactions on Machine Learning in Communications and Networking
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11070312/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849428409348784128
author Van-Doan Nguyen
Abebe Diro
Naveen Chilamkurti
Will Heyne
Khoa Tran Phan
author_facet Van-Doan Nguyen
Abebe Diro
Naveen Chilamkurti
Will Heyne
Khoa Tran Phan
author_sort Van-Doan Nguyen
collection DOAJ
description In this research, we proposed a novel anomaly detection system (ADS) that integrates federated learning (FL) with blockchain for resource-constrained IoT. The proposed system allows IoT devices to exchange machine learning (ML) models through a permissioned blockchain, enabling trustworthy collaborative learning through model sharing. To avoid single-point failure, any device can be a centre of the FL process. To deal with the issue of resource constraints in IoT devices and the model poisoning problem in FL, we introduced a novel method to use commitment coefficients and ML model discrepancies when selecting particular devices to join the FL process. We also proposed an efficient heuristic method to aggregate a federated model from a list of ML models trained locally on the selected devices, which helps to improve the federated model’s anomaly detection ability. The experiment results with the popular N-BaIoT dataset for IoT botnet attack detection show that the proposed system is more effective in detecting anomalies and resisting poisoning attacks than the two baselines (FedProx and FedAvg).
format Article
id doaj-art-b4a40924c66f4127a345d8b23218e278
institution Kabale University
issn 2831-316X
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Machine Learning in Communications and Networking
spelling doaj-art-b4a40924c66f4127a345d8b23218e2782025-08-20T03:28:43ZengIEEEIEEE Transactions on Machine Learning in Communications and Networking2831-316X2025-01-01379881310.1109/TMLCN.2025.358584211070312A Novel Blockchain-Enabled Federated Learning Scheme for IoT Anomaly DetectionVan-Doan Nguyen0https://orcid.org/0000-0001-5834-3709Abebe Diro1https://orcid.org/0000-0001-7147-2783Naveen Chilamkurti2https://orcid.org/0000-0002-5396-8897Will Heyne3https://orcid.org/0009-0005-9230-5542Khoa Tran Phan4https://orcid.org/0000-0003-0471-9402Department of Computer Science and IT, La Trobe University, Melbourne, VIC, AustraliaCollege of Business and Law, RMIT University, Melbourne, VIC, AustraliaDepartment of Computer Science and IT, La Trobe University, Melbourne, VIC, AustraliaBAE Systems Australia, Adelaide, VIC, AustraliaDepartment of Computer Science and IT, La Trobe University, Melbourne, VIC, AustraliaIn this research, we proposed a novel anomaly detection system (ADS) that integrates federated learning (FL) with blockchain for resource-constrained IoT. The proposed system allows IoT devices to exchange machine learning (ML) models through a permissioned blockchain, enabling trustworthy collaborative learning through model sharing. To avoid single-point failure, any device can be a centre of the FL process. To deal with the issue of resource constraints in IoT devices and the model poisoning problem in FL, we introduced a novel method to use commitment coefficients and ML model discrepancies when selecting particular devices to join the FL process. We also proposed an efficient heuristic method to aggregate a federated model from a list of ML models trained locally on the selected devices, which helps to improve the federated model’s anomaly detection ability. The experiment results with the popular N-BaIoT dataset for IoT botnet attack detection show that the proposed system is more effective in detecting anomalies and resisting poisoning attacks than the two baselines (FedProx and FedAvg).https://ieeexplore.ieee.org/document/11070312/Anomaly detectionblockchaincybersecurityfederated learningInternet of Thingssatellite networks
spellingShingle Van-Doan Nguyen
Abebe Diro
Naveen Chilamkurti
Will Heyne
Khoa Tran Phan
A Novel Blockchain-Enabled Federated Learning Scheme for IoT Anomaly Detection
IEEE Transactions on Machine Learning in Communications and Networking
Anomaly detection
blockchain
cybersecurity
federated learning
Internet of Things
satellite networks
title A Novel Blockchain-Enabled Federated Learning Scheme for IoT Anomaly Detection
title_full A Novel Blockchain-Enabled Federated Learning Scheme for IoT Anomaly Detection
title_fullStr A Novel Blockchain-Enabled Federated Learning Scheme for IoT Anomaly Detection
title_full_unstemmed A Novel Blockchain-Enabled Federated Learning Scheme for IoT Anomaly Detection
title_short A Novel Blockchain-Enabled Federated Learning Scheme for IoT Anomaly Detection
title_sort novel blockchain enabled federated learning scheme for iot anomaly detection
topic Anomaly detection
blockchain
cybersecurity
federated learning
Internet of Things
satellite networks
url https://ieeexplore.ieee.org/document/11070312/
work_keys_str_mv AT vandoannguyen anovelblockchainenabledfederatedlearningschemeforiotanomalydetection
AT abebediro anovelblockchainenabledfederatedlearningschemeforiotanomalydetection
AT naveenchilamkurti anovelblockchainenabledfederatedlearningschemeforiotanomalydetection
AT willheyne anovelblockchainenabledfederatedlearningschemeforiotanomalydetection
AT khoatranphan anovelblockchainenabledfederatedlearningschemeforiotanomalydetection
AT vandoannguyen novelblockchainenabledfederatedlearningschemeforiotanomalydetection
AT abebediro novelblockchainenabledfederatedlearningschemeforiotanomalydetection
AT naveenchilamkurti novelblockchainenabledfederatedlearningschemeforiotanomalydetection
AT willheyne novelblockchainenabledfederatedlearningschemeforiotanomalydetection
AT khoatranphan novelblockchainenabledfederatedlearningschemeforiotanomalydetection