A secure edge computing model using machine learning and IDS to detect and isolate intruders

Poornima Mahadevappa; Raja Kumar Murugesan; Redhwan Al-Amri; Reema Thabit; Abdullah Hussein Al-Ghushami; Gamal Alkawsi

doi:10.1016/j.mex.2024.102597

A secure edge computing model using machine learning and IDS to detect and isolate intruders

MethodsX. 2024 Feb 13:12:102597. doi: 10.1016/j.mex.2024.102597. eCollection 2024 Jun.

Authors

Poornima Mahadevappa¹, Raja Kumar Murugesan¹, Redhwan Al-Amri², Reema Thabit³, Abdullah Hussein Al-Ghushami⁴, Gamal Alkawsi⁵

Affiliations

¹ School of Computer Science and Engineering, Taylor's University, Malaysia.
² Centre for Professional Learning & Leadership, Institute of Education and Humanities, University of Wales Trinity Saint David, Swansea, UK.
³ Department of Computing, College of Computing and Informatics (CCI), Universiti Tenaga Nasional (UNITEN), Kajang, Selangor 43000, Malaysia.
⁴ Department of Information Technology, Community College of Qatar, Doha, Qatar.
⁵ Institute of Sustainable Energy, Universiti Tenaga Nasional, Kajang 43000, Malaysia.

Abstract

The article presents a secure edge computing model that utilizes machine learning for intrusion detection and isolation. It addresses the security challenges arising from the rapid expansion of IoT and edge computing. The proposed Intrusion Detection System (IDS) combines Linear Discriminant Analysis (LDA) and Logistic Regression (LR) to swiftly and accurately identify intrusions without alerting neighboring devices. The model outperforms existing solutions with an accuracy of 96.56%, precision of 95.78%, and quick training time (0.04 s). It is effective against various types of attacks, enhancing the security of edge networks for IoT applications. •The methodology employs a hybrid model that combines LDA and LR for intrusion detection.•Machine learning techniques are used to analyze and identify intrusive activities during data acquisition by edge nodes.•The methodology includes a mechanism to isolate suspected devices and data without notifying neighboring edge nodes to prevent intruders from gaining control over the edge network.

Keywords: Edge computing; Edge security; Hybrid LDA-LR; Intrusion detection; Intrusion isolation; LDA-LR; Machine learning.