Title: A critical review of feature selection methods for machine learning in IoT security

Authors: Jing Li; Mohd Shahizan Othman; Hewan Chen; Lizawati Mi Yusuf

Addresses: Faculty of Computing, Universiti Teknologi Malaysia (UTM), Malaysia ' Faculty of Computing, Universiti Teknologi Malaysia (UTM), Malaysia ' Digital Reform Research Center, China Jiliang University, China ' Faculty of Computing, Universiti Teknologi Malaysia, Malaysia

Abstract: In the internet of things (IoT) era, the security of connected devices and systems is critical. Machine learning models are commonly used for IoT attack detection, where feature selection (FS) plays an important role. However, FS for IoT security differs from traditional cybersecurity due to the uniqueness of IoT systems. This paper reviews FS methods for effective machine learning-based IoT attack detection. We identify five research questions and systematically review 1,272 studies, analysing 63 that meet inclusion criteria using the preferred reporting items for systematic review and meta-analysis (PRISMA) guidelines. We categorised the studies to address the research questions regarding FS methods, trends, practices, datasets and validation used. We also discussed FS limitations, challenges, and future research directions for IoT security. The review can serve as a reference for researchers and practitioners seeking to incorporate effective FS into machine learning-based IoT attack detection.

Keywords: internet of things; IoT; feature selection; IoT dataset; attack detection; classification; IoT security; systematic literature review; SLR; machine learning; deep learning.

DOI: 10.1504/IJCNDS.2024.138214

International Journal of Communication Networks and Distributed Systems, 2024 Vol.30 No.3, pp.264 - 312

Received: 06 Mar 2023
Accepted: 16 Apr 2023
Published online: 30 Apr 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article