Federated learning for intrusion detection in IoT environments: a privacy-preserving strategy

Abstract The rapid expansion of IoT devices has introduced significant cybersecurity risks, as attackers increasingly exploit these networks’ vulnerabilities. To counter this threat, this paper presents the Privacy-Enhanced IoT Defence System (PEIoT-DS), a novel solution that emphasises data privacy...

Full description

Saved in:
Bibliographic Details
Main Authors: Ansam Khraisat, Ammar Alazab, Moutaz Alazab, Areej Obeidat, Sarabjot Singh, Tony Jan
Format: Article
Language:English
Published: Springer 2025-06-01
Series:Discover Internet of Things
Subjects:
Online Access:https://doi.org/10.1007/s43926-025-00169-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850207509671837696
author Ansam Khraisat
Ammar Alazab
Moutaz Alazab
Areej Obeidat
Sarabjot Singh
Tony Jan
author_facet Ansam Khraisat
Ammar Alazab
Moutaz Alazab
Areej Obeidat
Sarabjot Singh
Tony Jan
author_sort Ansam Khraisat
collection DOAJ
description Abstract The rapid expansion of IoT devices has introduced significant cybersecurity risks, as attackers increasingly exploit these networks’ vulnerabilities. To counter this threat, this paper presents the Privacy-Enhanced IoT Defence System (PEIoT-DS), a novel solution that emphasises data privacy while delivering high-performance intrusion detection. PEIoT-DS use federated learning to create a comprehensive intrusion detection model without necessitating the transmission of raw data to a central server. IoT devices only contribute model updates, which are then combined to improve the global model. While allowing devices to benefit from the network’s collective insights, this decentralised learning methodology safeguards data privacy. Using a real-world IoT dataset and two popular federated learning algorithms—Federated Average and Federated Average with Momentum—the study assesses the effectiveness of PEIoT-DS. The findings show that, in comparison to Federated Average, Federated Average with Momentum produces faster convergence and better intrusion detection accuracy. Our PEIoT-DS approach offers a reliable intrusion detection system for IoT networks while maintaining privacy.
format Article
id doaj-art-3a09d9db9ab3452c99e46bca8d2cdf40
institution OA Journals
issn 2730-7239
language English
publishDate 2025-06-01
publisher Springer
record_format Article
series Discover Internet of Things
spelling doaj-art-3a09d9db9ab3452c99e46bca8d2cdf402025-08-20T02:10:31ZengSpringerDiscover Internet of Things2730-72392025-06-015111710.1007/s43926-025-00169-7Federated learning for intrusion detection in IoT environments: a privacy-preserving strategyAnsam Khraisat0Ammar Alazab1Moutaz Alazab2Areej Obeidat3Sarabjot Singh4Tony Jan5Deakin Cyber Research and Innovation Centre, Deakin UniversityCentre for Artificial Intelligence and Optimization, Torrens UniversityFaculty of Artificial Intelligence, Al-Balqa Applied University (BAU)Independent ResearcherDeakin Cyber Research and Innovation Centre, Deakin UniversityCentre for Artificial Intelligence and Optimization, Torrens UniversityAbstract The rapid expansion of IoT devices has introduced significant cybersecurity risks, as attackers increasingly exploit these networks’ vulnerabilities. To counter this threat, this paper presents the Privacy-Enhanced IoT Defence System (PEIoT-DS), a novel solution that emphasises data privacy while delivering high-performance intrusion detection. PEIoT-DS use federated learning to create a comprehensive intrusion detection model without necessitating the transmission of raw data to a central server. IoT devices only contribute model updates, which are then combined to improve the global model. While allowing devices to benefit from the network’s collective insights, this decentralised learning methodology safeguards data privacy. Using a real-world IoT dataset and two popular federated learning algorithms—Federated Average and Federated Average with Momentum—the study assesses the effectiveness of PEIoT-DS. The findings show that, in comparison to Federated Average, Federated Average with Momentum produces faster convergence and better intrusion detection accuracy. Our PEIoT-DS approach offers a reliable intrusion detection system for IoT networks while maintaining privacy.https://doi.org/10.1007/s43926-025-00169-7Federated learningData privacyCommunication network securityAnomaly detectionIntrusion detection system
spellingShingle Ansam Khraisat
Ammar Alazab
Moutaz Alazab
Areej Obeidat
Sarabjot Singh
Tony Jan
Federated learning for intrusion detection in IoT environments: a privacy-preserving strategy
Discover Internet of Things
Federated learning
Data privacy
Communication network security
Anomaly detection
Intrusion detection system
title Federated learning for intrusion detection in IoT environments: a privacy-preserving strategy
title_full Federated learning for intrusion detection in IoT environments: a privacy-preserving strategy
title_fullStr Federated learning for intrusion detection in IoT environments: a privacy-preserving strategy
title_full_unstemmed Federated learning for intrusion detection in IoT environments: a privacy-preserving strategy
title_short Federated learning for intrusion detection in IoT environments: a privacy-preserving strategy
title_sort federated learning for intrusion detection in iot environments a privacy preserving strategy
topic Federated learning
Data privacy
Communication network security
Anomaly detection
Intrusion detection system
url https://doi.org/10.1007/s43926-025-00169-7
work_keys_str_mv AT ansamkhraisat federatedlearningforintrusiondetectioniniotenvironmentsaprivacypreservingstrategy
AT ammaralazab federatedlearningforintrusiondetectioniniotenvironmentsaprivacypreservingstrategy
AT moutazalazab federatedlearningforintrusiondetectioniniotenvironmentsaprivacypreservingstrategy
AT areejobeidat federatedlearningforintrusiondetectioniniotenvironmentsaprivacypreservingstrategy
AT sarabjotsingh federatedlearningforintrusiondetectioniniotenvironmentsaprivacypreservingstrategy
AT tonyjan federatedlearningforintrusiondetectioniniotenvironmentsaprivacypreservingstrategy