A contrastive learning and knowledge distillation-based framework for efficient federated intrusion detection in IoT

In the era of pervasive connectivity, the widespread deployment of Internet of Things (IoT) devices across various applications has led to a rise in malicious attacks, necessitating the development of robust network intrusion detection systems (IDS) for IoT. Traditional deep learning-based IDS are c...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Ma, Jicheng He, Kai Lu, Dan Wang, Long Yin, Zhaokun Li
Format: Article
Language:English
Published: Taylor & Francis Group 2025-12-01
Series:Systems Science & Control Engineering
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/21642583.2025.2518963
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850219240140832768
author Li Ma
Jicheng He
Kai Lu
Dan Wang
Long Yin
Zhaokun Li
author_facet Li Ma
Jicheng He
Kai Lu
Dan Wang
Long Yin
Zhaokun Li
author_sort Li Ma
collection DOAJ
description In the era of pervasive connectivity, the widespread deployment of Internet of Things (IoT) devices across various applications has led to a rise in malicious attacks, necessitating the development of robust network intrusion detection systems (IDS) for IoT. Traditional deep learning-based IDS are challenged by the diversity of IoT devices, resource constraints, and the non-identically and independently distributed (non-IID) nature of IoT data. To address these issues, this paper introduces two solutions: CF-IDS and KF-IDS. CF-IDS is a federated learning-based IDS designed for cloud environments, preserving data privacy and addressing non-IID challenges. It utilizes contrastive learning and clustering to create pseudo-labels for public datasets, improving cold-start performance by aligning client models in the early training process. KF-IDS, as an additional (but optional) subsequent step of CF-IDS, based on knowledge distillation and mutual information theory, provides a off-line IDS solution by distillating CF-IDS into lite models. Through local deployment on low-computational-power end devices, KF-IDS avoiding upload raw data to the cloud. Experimental evaluations on public IoT datasets demonstrate that CF-IDS achieves 80.71% accuracy in non-IID scenarios, outperforming other federated learning methods such as FedNova. KF-IDS reduces time consumption by 46.81% and memory usage by 48.30% than CF-IDS while maintaining accuracy, which emphasizes the low cost of KF-IDS, such as deployed on affordable NVIDIA Jetson Nano rather than expensive RTX 4090 or Tesla A100.
format Article
id doaj-art-6ce5ca1669194ee29af5cb5dc0acc54d
institution OA Journals
issn 2164-2583
language English
publishDate 2025-12-01
publisher Taylor & Francis Group
record_format Article
series Systems Science & Control Engineering
spelling doaj-art-6ce5ca1669194ee29af5cb5dc0acc54d2025-08-20T02:07:27ZengTaylor & Francis GroupSystems Science & Control Engineering2164-25832025-12-0113110.1080/21642583.2025.2518963A contrastive learning and knowledge distillation-based framework for efficient federated intrusion detection in IoTLi Ma0Jicheng He1Kai Lu2Dan Wang3Long Yin4Zhaokun Li5Beijing Kedong Electric Power Control System Co.Ltd., Beijing, People's Republic of ChinaBeijing Kedong Electric Power Control System Co.Ltd., Beijing, People's Republic of ChinaBeijing Kedong Electric Power Control System Co.Ltd., Beijing, People's Republic of ChinaBeijing Kedong Electric Power Control System Co.Ltd., Beijing, People's Republic of ChinaSoftware College, Northeastern University, Shenyang, People's Republic of ChinaSoftware College, Northeastern University, Shenyang, People's Republic of ChinaIn the era of pervasive connectivity, the widespread deployment of Internet of Things (IoT) devices across various applications has led to a rise in malicious attacks, necessitating the development of robust network intrusion detection systems (IDS) for IoT. Traditional deep learning-based IDS are challenged by the diversity of IoT devices, resource constraints, and the non-identically and independently distributed (non-IID) nature of IoT data. To address these issues, this paper introduces two solutions: CF-IDS and KF-IDS. CF-IDS is a federated learning-based IDS designed for cloud environments, preserving data privacy and addressing non-IID challenges. It utilizes contrastive learning and clustering to create pseudo-labels for public datasets, improving cold-start performance by aligning client models in the early training process. KF-IDS, as an additional (but optional) subsequent step of CF-IDS, based on knowledge distillation and mutual information theory, provides a off-line IDS solution by distillating CF-IDS into lite models. Through local deployment on low-computational-power end devices, KF-IDS avoiding upload raw data to the cloud. Experimental evaluations on public IoT datasets demonstrate that CF-IDS achieves 80.71% accuracy in non-IID scenarios, outperforming other federated learning methods such as FedNova. KF-IDS reduces time consumption by 46.81% and memory usage by 48.30% than CF-IDS while maintaining accuracy, which emphasizes the low cost of KF-IDS, such as deployed on affordable NVIDIA Jetson Nano rather than expensive RTX 4090 or Tesla A100.https://www.tandfonline.com/doi/10.1080/21642583.2025.2518963Internet of thingsfederated learningintrusion detectionartificial intelligence
spellingShingle Li Ma
Jicheng He
Kai Lu
Dan Wang
Long Yin
Zhaokun Li
A contrastive learning and knowledge distillation-based framework for efficient federated intrusion detection in IoT
Systems Science & Control Engineering
Internet of things
federated learning
intrusion detection
artificial intelligence
title A contrastive learning and knowledge distillation-based framework for efficient federated intrusion detection in IoT
title_full A contrastive learning and knowledge distillation-based framework for efficient federated intrusion detection in IoT
title_fullStr A contrastive learning and knowledge distillation-based framework for efficient federated intrusion detection in IoT
title_full_unstemmed A contrastive learning and knowledge distillation-based framework for efficient federated intrusion detection in IoT
title_short A contrastive learning and knowledge distillation-based framework for efficient federated intrusion detection in IoT
title_sort contrastive learning and knowledge distillation based framework for efficient federated intrusion detection in iot
topic Internet of things
federated learning
intrusion detection
artificial intelligence
url https://www.tandfonline.com/doi/10.1080/21642583.2025.2518963
work_keys_str_mv AT lima acontrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot
AT jichenghe acontrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot
AT kailu acontrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot
AT danwang acontrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot
AT longyin acontrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot
AT zhaokunli acontrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot
AT lima contrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot
AT jichenghe contrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot
AT kailu contrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot
AT danwang contrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot
AT longyin contrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot
AT zhaokunli contrastivelearningandknowledgedistillationbasedframeworkforefficientfederatedintrusiondetectioniniot