Saved in:
Bibliographic Details
Main Authors: Barzoki, Hossein Shaemi, Hafshejani, Amir Hossein Fathi, Montazerolghaem, Ahmadreza
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.19451
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916025872678912
author Barzoki, Hossein Shaemi
Hafshejani, Amir Hossein Fathi
Montazerolghaem, Ahmadreza
author_facet Barzoki, Hossein Shaemi
Hafshejani, Amir Hossein Fathi
Montazerolghaem, Ahmadreza
contents Detecting anomalies in Internet of Things (IoT) networks is a critical security challenge, often hampered by highly imbalanced and diverse network traffic datasets. Standard classifiers struggle to perform well across all traffic types. This paper proposes a hybrid detection model to address this challenge using the Bot-IoT dataset. Instead of a single complex classifier, we first employ K-Means clustering to segment the training data into three distinct traffic profile clusters. We then train and evaluate multiple baseline machine learning models, including Decision Tree, KNN, and XGBoost, on each cluster independently to identify the optimal classifier for that specific data profile. Our results show that this clusterspecific, hybrid approach, which assigns different simple models to different clusters, improves detection accuracy and provides a more robust and efficient framework for handling diverse IoT attack traffic.
format Preprint
id arxiv_https___arxiv_org_abs_2605_19451
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Hybrid Cluster-Based Classification Model for Anomaly Detection in Unbalanced IoT Networks
Barzoki, Hossein Shaemi
Hafshejani, Amir Hossein Fathi
Montazerolghaem, Ahmadreza
Networking and Internet Architecture
Detecting anomalies in Internet of Things (IoT) networks is a critical security challenge, often hampered by highly imbalanced and diverse network traffic datasets. Standard classifiers struggle to perform well across all traffic types. This paper proposes a hybrid detection model to address this challenge using the Bot-IoT dataset. Instead of a single complex classifier, we first employ K-Means clustering to segment the training data into three distinct traffic profile clusters. We then train and evaluate multiple baseline machine learning models, including Decision Tree, KNN, and XGBoost, on each cluster independently to identify the optimal classifier for that specific data profile. Our results show that this clusterspecific, hybrid approach, which assigns different simple models to different clusters, improves detection accuracy and provides a more robust and efficient framework for handling diverse IoT attack traffic.
title A Hybrid Cluster-Based Classification Model for Anomaly Detection in Unbalanced IoT Networks
topic Networking and Internet Architecture
url https://arxiv.org/abs/2605.19451