Original scientific paper

https://doi.org/10.17559/TV-20250108002248

Trust Aware Water Strider Optimization-Based Clustering with Intrusion Detection in IoT Environments

Nada Alzaben ; Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh 11671, Saudi Arabia
Mashael Maashi ; Department of Software Engineering, College of Computer and Information Sciences, King Saud University, Riyadh 11543, Saudi Arabia
Menwa Alshammeri ; Department of Computer Sciences, College of Computer and Information Sciences, Jouf University, Saudi Arabia
V. Saraswathi ; Department of Computer Science and Engineering, Chennai Institute of Technology, Chennai, India
R. Kiruba Buri ; Department of Computer Science Engineering, University College of Engineering, Pattukottai, Tamil Nadu-614704, India
S. Gayathri Priya ; Department of ECE, R.M.D. Engineering College, Kavaraipettai, India *

* Corresponding author.

Abstract

The Internet of Things (IoT) has emerged as a transformative technology revolutionizing domains such as healthcare, smart cities, and e-governance. However, real-time IoT integration faces significant hurdles due to the limited energy resources and computational capabilities of IoT devices. Additionally, security vulnerabilities in IoT systems amplify threats to the integrity and reliability of smart applications, necessitating robust solutions. This study introduces a novel Trust-Aware Improved Water Strider Optimization-based Clustering with Intrusion Detection System (TAIWSOC-IDS) for enhancing IoT environments' security and efficiency. The proposed framework comprises two key stages: clustering and intrusion detection. In the clustering stage, the TAIWSOC technique identifies clusters and cluster heads (CHs) by optimizing a fitness function that considers residual energy, communication distance, and trust metrics, ensuring balanced energy consumption and secure communication. In the intrusion detection stage, a Chaos Game Optimization (CGO)-enhanced Multihead Attention Bidirectional Long Short-Term Memory (MHA-BiLSTM) model is employed. The CGO algorithm optimally tunes the hyper parameters of the MHA-BiLSTM model, improving its ability to accurately classify normal and malicious activities. Experimental evaluation demonstrates that the TAIWSOC-IDS outperforms existing state-of-the-art methods in terms of energy efficiency, clustering reliability, and intrusion detection accuracy. The proposed system achieves enhanced detection rates while significantly reducing false positives, proving its efficacy in mitigating security threats. By addressing both energy efficiency and security concerns, TAIWSOC-IDS serves as a comprehensive framework for developing secure, sustainable, and efficient IoT applications across diverse real-time scenarios.

Keywords

chaos game optimization; internet of things (IoT); intrusion detection system (IDS); multihead attention BiLSTM; water strider optimization

Hrčak ID:

337728

URI

https://hrcak.srce.hr/337728

Publication date:

31.10.2025.

Visits: 117 *