article · Journal of Communications Software and Systems
Intrusion detection systems face challenges when processing large numbers of network features, which can slow down analysis and degrade performance. This research presents TUNA-FS, a feature selection framework that converts the continuous Tuna Swarm Optimization algorithm into a binary format suitable for selecting key features. By incorporating an adaptive V-shaped transfer function, the system balances the search between exploring new feature combinations and refining existing ones. It also applies a multi-objective fitness function aimed at lowering the total feature count, boosting detection accuracy, and cutting false alarms. When evaluated on the NSL-KDD and CIC-IDS2017 datasets, the framework successfully removed redundant data while maintaining strong detection rates across various classification models, including random forests and support vector machines.
Network defence tools often struggle with massive amounts of incoming traffic data, leading to sluggish analysis and false warnings. By stripping away irrelevant data points, this approach helps security systems identify cyber threats more accurately and rapidly. This ensures computer networks remain secure without overwhelming system resources or generating excessive false alarms.
This applied research demonstrates software-level effectiveness on standard benchmark datasets, indicating an applied and tested stage of development. The framework could enable cybersecurity vendors and network administrators to improve the speed and accuracy of intrusion detection products. However, commercial deployment would require integration and testing within live, operational network environments beyond static benchmark data.
AI-generated from the published abstract. Always read the original work before citing.
Feature selection is crucial for improving intrusion detection systems by addressing the curse of dimensionality and eliminating irrelevant features. However, applying continuous metaheuristics—such as the Tuna Swarm Optimization (TSO) algorithm—to this inherently binary problem requires effective binarization strategies. This paper presents TUNA-FS, a novel feature selection framework that employs a binary variant of the TSO algorithm. The proposed method introduces an adaptive V-shaped transfer function that dynamically manages the binarization process, maintaining a balance between exploration and exploitation throughout the search. Additionally, a multi-objective fitness function is used to jointly optimize key objectives: enhancing detection accuracy, reducing false alarms, and minimizing the number of selected features. The effectiveness of the approach is validated through comprehensive experiments on the NSL-KDD and CIC-IDS2017 benchmark datasets. Results demonstrate that the method achieves substantial feature reduction while maintaining high detection performance across multiple classifiers, including support vector machines, decision trees, random forests, and k-nearest neighbors. Comparative analysis against state-of-the-art methods confirms the competitiveness and balanced performance of the proposed framework, positioning it as an effective technique for enhancing intrusion detection efficiency and accuracy.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.24138/jcomss-2025-0083
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
