An Intrusion Detection System for the Internet of Things Based on Machine Learning: Review and Challenges

Ahmed Adnan,Abdullah Muhammed,Azizol Abdullah,Abdul Azim Abd Ghani,Fahrul Hakim

doi:10.3390/sym13061011

Ahmed Adnan, Abdullah Muhammed + Show 3 more

Open Access

https://doi.org/10.3390/sym13061011

Copy DOI

Journal: Symmetry	Publication Date: Jun 4, 2021
Citations: 24	License type: CC BY 4.0

Affiliation: Universiti Putra Malaysia

Abstract

An intrusion detection system (IDS) is an active research topic and is regarded as one of the important applications of machine learning. An IDS is a classifier that predicts the class of input records associated with certain types of attacks. In this article, we present a review of IDSs from the perspective of machine learning. We present the three main challenges of an IDS, in general, and of an IDS for the Internet of Things (IoT), in particular, namely concept drift, high dimensionality, and computational complexity. Studies on solving each challenge and the direction of ongoing research are addressed. In addition, in this paper, we dedicate a separate section for presenting datasets of an IDS. In particular, three main datasets, namely KDD99, NSL, and Kyoto, are presented. This article concludes that three elements of concept drift, high-dimensional awareness, and computational awareness that are symmetric in their effect and need to be addressed in the neural network (NN)-based model for an IDS in the IoT.

Highlights

The security of technology is a continuously developing and emerging topic
We presented a literature survey on the topic of an intrusion detection system (IDS) and its challenges
The focus of the article was on using machine learning for a IDS in the Internet of Things

Summary

Introduction

The security of technology is a continuously developing and emerging topic. More advancements of technologies lead to more vulnerability and threat of attacks. This has led researchers to exploit another aspect for protecting systems from attacks, which is data that is generated from almost every device It is well known, that recent technologies generate massive data from a wide range of sources, for example, smartphones which provide a source of multistream data from their sensor sets such as accelerometers, gyros, and global positioning system [1]. That recent technologies generate massive data from a wide range of sources, for example, smartphones which provide a source of multistream data from their sensor sets such as accelerometers, gyros, and global positioning system [1] It includes the Internet of Things (IoT), which has supported the emergence of new concepts of stream data generation such as health care IoT [2]

Objectives

Findings

Discussion

Conclusion