Hybrid Model for Novel Attack Detection Using a Cluster-Based Machine Learning Classification Approach for the Internet of Things (IoT)

To combat the growing danger of zero-day attacks on IoT networks, this study introduces a Cluster-Based Classification (CBC) method. Security vulnerabilities have become more apparent with the growth of IoT devices, calling for new approaches to identify unique threats quickly. The hybrid CBC approa...

Full description

Saved in:
Bibliographic Details
Main Authors: Naveed Ahmed, Md Asri Ngadi, Abdulaleem Ali Almazroi, Nouf Atiahallah Alghanmi
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Future Internet
Subjects:
Online Access:https://www.mdpi.com/1999-5903/17/6/251
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849431872944209920
author Naveed Ahmed
Md Asri Ngadi
Abdulaleem Ali Almazroi
Nouf Atiahallah Alghanmi
author_facet Naveed Ahmed
Md Asri Ngadi
Abdulaleem Ali Almazroi
Nouf Atiahallah Alghanmi
author_sort Naveed Ahmed
collection DOAJ
description To combat the growing danger of zero-day attacks on IoT networks, this study introduces a Cluster-Based Classification (CBC) method. Security vulnerabilities have become more apparent with the growth of IoT devices, calling for new approaches to identify unique threats quickly. The hybrid CBC approach uses optimized k-means clustering to find commonalities across different abnormalities, intending to quickly identify and classify unknown harmful attacks in a varied IoT network. The technique is fine-tuned for eight-class and two-class classifications, supporting different attacks using the IoTCIC2023 dataset and SelectKBest feature selection. Robust analysis is achieved by evaluating and aggregating the performance of machine learning classifiers such as XGBoost, AdaBoost, KNN, and Random Forest. In two-class classification, Random Forest achieves 95.11% accuracy, while in eight-class classification, KNN tops the charts with 88.24%. These results demonstrate noteworthy accuracy. The suggested CBC technique is effective, as shown by comparisons with state-of-the-art approaches. Despite several caveats and dataset specifications, this study provides a useful tool for academics and practitioners in the ever-changing field of cybersecurity by suggesting a method to strengthen the security of IoT networks against new threats.
format Article
id doaj-art-e6820dbab8b84e4f870bb1ade9e4edfd
institution Kabale University
issn 1999-5903
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Future Internet
spelling doaj-art-e6820dbab8b84e4f870bb1ade9e4edfd2025-08-20T03:27:29ZengMDPI AGFuture Internet1999-59032025-05-0117625110.3390/fi17060251Hybrid Model for Novel Attack Detection Using a Cluster-Based Machine Learning Classification Approach for the Internet of Things (IoT)Naveed Ahmed0Md Asri Ngadi1Abdulaleem Ali Almazroi2Nouf Atiahallah Alghanmi3Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru 81310, MalaysiaFaculty of Computing, Universiti Teknologi Malaysia, Johor Bahru 81310, MalaysiaDepartment of Information Technology, Faculty of Computing and Information Technology in Rabigh, King Abdulaziz University, Rabigh 21911, Saudi ArabiaDepartment of Information Technology, Faculty of Computing and Information Technology in Rabigh, King Abdulaziz University, Rabigh 21911, Saudi ArabiaTo combat the growing danger of zero-day attacks on IoT networks, this study introduces a Cluster-Based Classification (CBC) method. Security vulnerabilities have become more apparent with the growth of IoT devices, calling for new approaches to identify unique threats quickly. The hybrid CBC approach uses optimized k-means clustering to find commonalities across different abnormalities, intending to quickly identify and classify unknown harmful attacks in a varied IoT network. The technique is fine-tuned for eight-class and two-class classifications, supporting different attacks using the IoTCIC2023 dataset and SelectKBest feature selection. Robust analysis is achieved by evaluating and aggregating the performance of machine learning classifiers such as XGBoost, AdaBoost, KNN, and Random Forest. In two-class classification, Random Forest achieves 95.11% accuracy, while in eight-class classification, KNN tops the charts with 88.24%. These results demonstrate noteworthy accuracy. The suggested CBC technique is effective, as shown by comparisons with state-of-the-art approaches. Despite several caveats and dataset specifications, this study provides a useful tool for academics and practitioners in the ever-changing field of cybersecurity by suggesting a method to strengthen the security of IoT networks against new threats.https://www.mdpi.com/1999-5903/17/6/251IoT securitynovel attack detectioncluster-based classification
spellingShingle Naveed Ahmed
Md Asri Ngadi
Abdulaleem Ali Almazroi
Nouf Atiahallah Alghanmi
Hybrid Model for Novel Attack Detection Using a Cluster-Based Machine Learning Classification Approach for the Internet of Things (IoT)
Future Internet
IoT security
novel attack detection
cluster-based classification
title Hybrid Model for Novel Attack Detection Using a Cluster-Based Machine Learning Classification Approach for the Internet of Things (IoT)
title_full Hybrid Model for Novel Attack Detection Using a Cluster-Based Machine Learning Classification Approach for the Internet of Things (IoT)
title_fullStr Hybrid Model for Novel Attack Detection Using a Cluster-Based Machine Learning Classification Approach for the Internet of Things (IoT)
title_full_unstemmed Hybrid Model for Novel Attack Detection Using a Cluster-Based Machine Learning Classification Approach for the Internet of Things (IoT)
title_short Hybrid Model for Novel Attack Detection Using a Cluster-Based Machine Learning Classification Approach for the Internet of Things (IoT)
title_sort hybrid model for novel attack detection using a cluster based machine learning classification approach for the internet of things iot
topic IoT security
novel attack detection
cluster-based classification
url https://www.mdpi.com/1999-5903/17/6/251
work_keys_str_mv AT naveedahmed hybridmodelfornovelattackdetectionusingaclusterbasedmachinelearningclassificationapproachfortheinternetofthingsiot
AT mdasringadi hybridmodelfornovelattackdetectionusingaclusterbasedmachinelearningclassificationapproachfortheinternetofthingsiot
AT abdulaleemalialmazroi hybridmodelfornovelattackdetectionusingaclusterbasedmachinelearningclassificationapproachfortheinternetofthingsiot
AT noufatiahallahalghanmi hybridmodelfornovelattackdetectionusingaclusterbasedmachinelearningclassificationapproachfortheinternetofthingsiot