Machine Learning Techniques for Enhanced Intrusion Detection in IoT Security

Network Intrusion Detection Systems (NIDSs) are fundamental to safeguarding computer networks. Intrusion detection systems must become more effective as new attacks are developed and networks grow. Anomaly-based automated detection stands out due to its superior performance among the various detecti...

Full description

Saved in:
Bibliographic Details
Main Authors: Hanadi Hakami, Muhammad Faheem, Majid Bashir Ahmad
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10887215/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849720438544924672
author Hanadi Hakami
Muhammad Faheem
Majid Bashir Ahmad
author_facet Hanadi Hakami
Muhammad Faheem
Majid Bashir Ahmad
author_sort Hanadi Hakami
collection DOAJ
description Network Intrusion Detection Systems (NIDSs) are fundamental to safeguarding computer networks. Intrusion detection systems must become more effective as new attacks are developed and networks grow. Anomaly-based automated detection stands out due to its superior performance among the various detection techniques. However, with the increasing complexity and frequency of cyberattacks, managing vast amounts of data remains challenging for anomaly-based NIDS. Therefore, it is necessary to find an efficient method for solving the problem by using classification with an intrusion detection system which analyzes enormous amounts of traffic data. This research introduces a new model that leverages machine learning (ML) and deep learning (DL) to enhance detection effectiveness and ensure reliability. The approach optimizes data preprocessing by integrating SMOTE for effective data balancing and Pearson’s Correlation Coefficient (PCC) for feature selection. We compared several ML and DL techniques to detect and address the most efficient one for our pipeline. Compared with other approaches, LSTM and RF show superior results when tested on the WSN-DS, UNSW-NB15, and CIC-IDS 2017 datasets. Additionally, the proposed solution prevents biases from arising by addressing imbalanced datasets.
format Article
id doaj-art-ed95f93aaca64005b7712b66b3f8ff6d
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-ed95f93aaca64005b7712b66b3f8ff6d2025-08-20T03:11:55ZengIEEEIEEE Access2169-35362025-01-0113311403115810.1109/ACCESS.2025.354222710887215Machine Learning Techniques for Enhanced Intrusion Detection in IoT SecurityHanadi Hakami0https://orcid.org/0000-0001-5627-6805Muhammad Faheem1https://orcid.org/0009-0000-2274-6821Majid Bashir Ahmad2https://orcid.org/0009-0009-0760-3529Department of Software Engineering, College of Engineering, University of Business and Technology, Jeddah, Saudi ArabiaSchool of Technology and Innovations, University of Vaasa, Vaasa, FinlandDepartment of Computer Sciences, COMSATS University Islamabad, Vehari, PakistanNetwork Intrusion Detection Systems (NIDSs) are fundamental to safeguarding computer networks. Intrusion detection systems must become more effective as new attacks are developed and networks grow. Anomaly-based automated detection stands out due to its superior performance among the various detection techniques. However, with the increasing complexity and frequency of cyberattacks, managing vast amounts of data remains challenging for anomaly-based NIDS. Therefore, it is necessary to find an efficient method for solving the problem by using classification with an intrusion detection system which analyzes enormous amounts of traffic data. This research introduces a new model that leverages machine learning (ML) and deep learning (DL) to enhance detection effectiveness and ensure reliability. The approach optimizes data preprocessing by integrating SMOTE for effective data balancing and Pearson’s Correlation Coefficient (PCC) for feature selection. We compared several ML and DL techniques to detect and address the most efficient one for our pipeline. Compared with other approaches, LSTM and RF show superior results when tested on the WSN-DS, UNSW-NB15, and CIC-IDS 2017 datasets. Additionally, the proposed solution prevents biases from arising by addressing imbalanced datasets.https://ieeexplore.ieee.org/document/10887215/Intrusion detectionIoTclassificationmachine/deep learningrandom forestslong-short-term-memory
spellingShingle Hanadi Hakami
Muhammad Faheem
Majid Bashir Ahmad
Machine Learning Techniques for Enhanced Intrusion Detection in IoT Security
IEEE Access
Intrusion detection
IoT
classification
machine/deep learning
random forests
long-short-term-memory
title Machine Learning Techniques for Enhanced Intrusion Detection in IoT Security
title_full Machine Learning Techniques for Enhanced Intrusion Detection in IoT Security
title_fullStr Machine Learning Techniques for Enhanced Intrusion Detection in IoT Security
title_full_unstemmed Machine Learning Techniques for Enhanced Intrusion Detection in IoT Security
title_short Machine Learning Techniques for Enhanced Intrusion Detection in IoT Security
title_sort machine learning techniques for enhanced intrusion detection in iot security
topic Intrusion detection
IoT
classification
machine/deep learning
random forests
long-short-term-memory
url https://ieeexplore.ieee.org/document/10887215/
work_keys_str_mv AT hanadihakami machinelearningtechniquesforenhancedintrusiondetectioniniotsecurity
AT muhammadfaheem machinelearningtechniquesforenhancedintrusiondetectioniniotsecurity
AT majidbashirahmad machinelearningtechniquesforenhancedintrusiondetectioniniotsecurity