Safeguarding Networks From Malicious Intrusions Using Quantum Machine Intelligence
- 23 June 2025
- journal article
- Published by Wiley in Software: Practice and Experience
- Vol. 55 (10) , 1676-1695
Abstract
In recent centuries, the fast growth of Internet of Things (IoT) networks has posed serious security vulnerabilities due to heterogeneous devices, evolving attack patterns, and privacy concerns. To encounter security measures, several intrusion detection solutions have been explored based on machine learning, which are reasonably effective in static environments to protect against malicious attacks. In order to defend against modern attacks, unfortunately, fundamental machine learning techniques have not considered accumulation, reuse of knowledge, and sensitivity of the detection model in dynamic environments. Keeping in attention to encounter the aforementioned limitations, in this study, we developed a security model using the grasshopper optimization algorithm (GOA), adding quantum effect to enhance the power of IoT security networks, called QMGOA. Additionally, by integration of quantum effects, the GOA approach improves exploitation capabilities, search efficiency in the feature space, and bridges the gap between exploration and exploitation processes. Furthermore, a multi‐population strategy is employed to strengthen QGOA for making more diverse solutions. Moreover, differential evolution (DE) is used in QMGOA to refine further solution quality. The proposed approach is evaluated on three datasets, such as NSL‐KDD, BoT‐IoT, and UNSW‐NB15, to determine noteworthy features and its efficacy in IoT environments. The experimental analysis further reveals that the proposed method generates better balance solutions with less execution time and outperforms state‐of‐the‐art approaches.Keywords
This publication has 63 references indexed in Scilit:
- Optimizing quantum machine learning for proactive cybersecurityOptimization and Engineering, 2024
- Interrelated dynamic biased feature selection and classification model using enhanced gorilla troops optimizer for intrusion detectionAlexandria Engineering Journal, 2024
- iQuantum: A toolkit for modeling and simulation of quantum computing environmentsSoftware: Practice and Experience, 2024
- Deep Q-network-based heuristic intrusion detection against edge-based SIoT zero-day attacksApplied Soft Computing, 2023
- Quantum-inspired evolutionary algorithm applied to neural architecture searchApplied Soft Computing, 2022
- Detecting anonymous attacks in wireless communication medium using adaptive grasshopper optimization algorithmCognitive Systems Research, 2021
- Chaos teaching learning based algorithm for large‐scale global optimization problem and its applicationConcurrency and Computation: Practice and Experience, 2021
- Frame-by-frame Wi-Fi attack detection algorithm with scalable and modular machine-learning designApplied Soft Computing, 2020
- Stacked pruning sparse denoising autoencoder based intelligent fault diagnosis of rolling bearingsApplied Soft Computing, 2020
- A metaheuristic optimization approach for energy efficiency in the IoT networksSoftware: Practice and Experience, 2020