Title: Multi-tier ensemble-based approach for threat detection in IoT security

Authors: Sriram Parabrahmachari; Srinivasan Narayanasamy

Addresses: Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology (Deemed to be University), Chennai – 600119, Tamil Nadu, India ' Department of Computer Science and Engineering, Rajalakshmi Engineering College, Chennai – 600119, Tamil Nadu, India

Abstract: With the rise of IoT devices, security vulnerabilities have increased, making traditional measures inadequate. Soft computing and machine learning offer adaptive threat detection by identifying patterns and anomalies. This paper presents a hierarchical ensemble-based approach for IoT security, where multiple classifiers collaborate to detect various threats. Trained on diverse datasets, these classifiers enhance accuracy through ensemble learning. Evaluated on a public dataset, the proposed approach outperforms state-of-the-art methods in accuracy, precision, and recall. It ensures high detection rates with low computational costs, making it a promising solution for securing IoT networks against cyber threats.

Keywords: threat detection system; IoT security; soft computing; machine learning; hierarchical ensembling.

DOI: 10.1504/IJSNET.2025.146127

International Journal of Sensor Networks, 2025 Vol.48 No.1, pp.30 - 43

Received: 21 Jul 2024
Accepted: 17 Feb 2025
Published online: 07 May 2025 *

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