Citation

Arif, Malik Huzaifa and Attaullah, Hafiz Muhammad and Nishat, Farhood and Imdad, Maria and Nawaz, Menaa and Khan, Inam Ullah (2026) Multi-Dataset Comparative Analysis of Genetic Algorithms for Intrusion Detection in UAV Networks. In: Proceedings of the 3rd International Conference on Emerging Trends and Innovation (3rd ICETI). Springer Nature, pp. 51-63. ISBN 978-3-032-22425-5, 978-3-032-22426-2

Text Multi-Dataset Comparative Analysis of Genetic Algorithms for Intrusion Detection in UAV Networks _ Springer Nature Link.pdf - Published Version Restricted to Repository staff only Download (736kB)

Abstract

Intrusion Detection Systems are essential for safeguarding Unmanned Aerial Vehicle communication networks from a growing range of cyber threats. This study presents a multi-dataset comparative analysis of five Genetic Algorithm based feature selection techniques tailored for UAV network security. Three diverse and augmented datasets, CTGAN-UNSW-NB15, CTGAN-CIC-IDS2017, and the UAV-specific T-ITS are used to evaluate the effectiveness of GA-enhanced feature selection. Five traditional classifiers (LightGBM, Random Forest, Decision Tree, K-Nearest Neighbors, and Naïve Bayes) are trained on GA-optimized features, with results showing consistent improvements in accuracy, precision, recall, and F1-score across all datasets. Heatmaps and confusion matrices further validate the effectiveness of the selected features, particularly in identifying both common and UAV-specific attacks. The findings confirm the suitability of GA-based optimization for developing lightweight, high-performance IDS solutions capable of operating under the computational constraints typical of UAV systems.

Item Type:	Book Section
Uncontrolled Keywords:	UAVAnomaly detection
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	05 Oct 2026 02:29
Last Modified:	05 Oct 2026 02:29
URII:	http://shdl.mmu.edu.my/id/eprint/16859

Downloads

Edit (login required)