A Survey on Supervised Machine Learning in Intrusion Detection Systems for Internet of Things

Aug 3, 2026

Upload by Eliana

The Internet of Things (IoT) is growing rapidly, driving increases in network traffic and exposing new security vulnerabilities that attract cybercriminal activity. Intrusion detection systems (IDS) are used to identify network attacks and protect network resources, yet achieving stable, high-accuracy detection is challenging due to data issues such as irrelevant and excessive features. The paper surveys prevailing supervised machine learning techniques applied to IDS research in IoT, aiming to provide clearer insight into approaches that can improve detection accuracy while controlling false alarms.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages1

Reading Time3 min

AccessFree to download

Introduction

Role and importance of IDS in network security

Relationship between IDS and preventive tools like firewalls

Forensic evidence and incident response

A Survey on Supervised Machine Learning in Intrusion Detection Systems for Internet of Things 2023 IEEE 8th International Conference On Software Engineering and Computer Systems (ICSECS) ©2023 IEEE DOI: 10.1109/ICSECS58457.2023.10256275| 979-8-3503-1093-1/23/$31.00 | Shakirah Binti Saidin Faculty of Computing Universiti Malaysia Pahang AlSultan Abdullah Kuantan, Pahang, Malaysia [shakirah.saidin90@gmail.com](shakirah.saidin90@gmail.com) Dr Syifak Binti Izhar Hisham* Faculty of Computing Universiti Malaysia Pahang AlSultan Abdullah Kuantan, Pahang, Malaysia [syifak@ump.edu.m](syifak@ump.edu.my)[y](syifak@ump.edu.my) Abstract—The Internet of Things (IoT) is expanding exponentially, increasing network traffic flow. This trend causes network security vulnerabilities and draws the attention of cybercriminals. Consequently, an intrusion detection system is designed to identify various network attacks and provide network resource protection. On the other hand, building a steadfast intrusion detection system is difficult since there are numerous flaws to address, such as the presence of supernumerary and irrelevant features in the dataset, leading to low detection accuracy and a high false alarm rate. To address these flaws, researchers are attempting to research on applying supervised machine learning techniques in intrusion detection systems for IoT. Therefore, this paper explores the prevailing machine learning techniques utilized in the intrusion detection system research area to provide better insight in this field. Keywords—supervised machine learning, intrusion detection system, security, Internet of Things I. INTRODUCTION Intrusion Detection System (IDS) is prominent as one of the solutions for system security alongside firewalls and antivirus. However, as researchers continue their search for an intrusion detection technology with high detection accuracy, the performance of an IDS has become a fundamental issue[1]. IDSs are critical components of security as they will try to protect the systems from intruders. It works by monitoring systems or networks for anomalous and malicious behaviors [2] . An IDS’s purpose is to identify any security breaches in a network [3]. It will gather and analyze data about a network’s important notes to determine whether any security policies have been breached or if there are indicators of an attack. Incorporating IDSs is crucial in conjunction with preventive security tools like firewalls because they identify and expose attacks that exploit vulnerabilities or glitches within the systems. Furthermore, they offer valuable forensic evidence that aids system administrators in effectively responding to cyber-attacks [4] . Fig. 1. Taxonomy of Machine Learning Model[15] 979-8-3503-1093-1/23/$31 .00 ©2023 IEEE 419 Authorized licensed use limited to: Universiti Malaysia Pahang Al Sultan Abdullah (UMPSA) .. Downloaded on February 06,2024 at 08:01:16 UTC from IEEE Xplore. Restrictions apply.

FAQs

Why is intrusion detection important in IoT networks?

Intrusion detection systems protect systems by monitoring for anomalous and malicious behavior, identifying security breaches in networks and gathering data to determine whether attacks are indicated.

What challenges affect intrusion detection accuracy?

Stable IDS performance is difficult due to dataset flaws such as supernumerary and irrelevant features, which can reduce detection accuracy and increase false alarm rates.

How does the paper contribute to IDS research for IoT?

It explores prevailing supervised machine learning techniques used in intrusion detection system research for IoT to provide better insight into improving detection outcomes.

Aug 3, 2026

Upload by Eliana