Izvorni znanstveni članak

https://doi.org/10.17559/TV-20241130002158

Quantum Chameleon Swarm Optimizer-Based Feature Selection with Deep Learning for Intrusion Detection in Blockchain-Enabled IoT Environments

Usha Subramaniam orcid.org/0009-0005-0642-2356 ; Department of Computer Science and Engineering, University College of Engineering BIT Campus, Anna University, Tiruchirappalli, India *
Sudhakar Thiruvenkatasamy ; Department - Computer Science and Engineering, Nandha College of Technology, Erode - 638052, India
Eatedal Alabdulkreem ; Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi Arabia
Nuha Alruwais ; Department of Computer Science and Engineering, College of Applied Studies and Community Services, King Saud University, Saudi Arabia, P.O. Box 22459, Riyadh 11495, Saudi Arabia

* Dopisni autor.

Sažetak

As the number of networked devices continues to rise, Internet of Things (IoT) settings are becoming increasingly susceptible to cyberattacks. As a result, intrusion detection systems (IDS) are becoming increasingly important in these environments. In order to identify unwanted access or abnormalities, an effective IDS observes the interactions between devices, the traffic on the network, and the behavior of users. Additionally, it enforces stringent access limits, encryption, and real-time monitoring. When it comes to protecting the integrity of IoT devices and data, prompt detection and reaction to security issues are very necessary. Blockchain technology, which has a distributed and tamper-proof ledger, offers a secure basis for IoT systems. However, it necessitates the implementation of complementing cybersecurity procedures. An approach known as Quantum Chameleon Swarm Optimizer-based Feature Selection with Deep Learning for Intrusion Detection (QCSOFS-DLID) is presented in this paper for use in Internet of Things scenarios that are enabled by Blockchain technology. An approach known as QCSOFS-DLID incorporates Blockchain technology for the purpose of ensuring secure communication, feature selection (FS) through the utilization of the proposed algorithm for the purpose of detecting attacks. Blockchain technology is used in the QCSOFS-DLID strategy to ensure that IoT systems have secure communication protocols. A Convolutional Variational Autoencoder (CVAE) model is utilized for the purpose of detecting intrusions, while the QCSO technique is utilized for the purpose of effective feature selection. Through the utilization of the Coot Optimization Algorithm (COA), the hyperparameters of the model are fine-tuned. In this study, the QCSOFS-DLID approach is assessed using the BoT-IoT dataset. The experimental findings reveal that the method's performance is superior to that of existing state-of-the-art methodologies through comparison. Blockchain technology, feature selection, and deep learning are all successfully integrated into this strategy, which aims to improve intrusion detection and further strengthen security in Internet of Things environments.

Ključne riječi

Blockchain; Deep learning; Internet of Things (IoT); Intrusion Detection System (IDS); Quantum Chameleon Swarm Optimizer (QCSO)

Hrčak ID:

335063

URI

https://hrcak.srce.hr/335063

Datum izdavanja:

30.8.2025.

Posjeta: 308 *