Ensemble Machine Learning Models Utilizing a Hybrid Recursive Feature Elimination (RFE) Technique for Detecting GPS Spoofing Attacks Against Unmanned Aerial Vehicles
Sensors · 09.04.2025 · 25 (8) · 2388
DOI: 10.3390/s25082388 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 09.04.2025. Verfasst von Raghad Al-Syouf und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Network Engineering and Security, Jordan University of Science and Technology, Irbid 22110, Jordan. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The dependency of Unmanned Aerial Vehicles (UAVs), also known as drones, on off-board data, such as control and position data, makes them highly susceptible to serious safety and security threats, including data interceptions, Global Positioning System (GPS) jamming, and spoofing attacks. This indeed necessitates the existence of an Intrusion Detection System (IDS) in place to detect potential security threats/intrusions promptly. Recently, machine-learning-based IDSs have gained popularity due to their high performance in detecting known as well as novel cyber-attacks. However, the time and computation efficiencies of ML-based IDSs still present a challenge in the UAV domain. Therefore, this paper proposes a hybrid Recursive Feature Elimination (RFE) technique based on feature importance ranking along with a Spearman Correlation Analysis (SCA). This technique is built on ensemble learning approaches, namely, bagging, boosting, stacking, and voting classifiers, to efficiently detect GPS spoofing attacks. Two benchmark datasets are employed: the GPS spoofing dataset and the UAV location GPS spoofing dataset. The results show that our proposed ensemble models achieved a notable balance between efficacy and efficiency, showing that the bagging classifier achieved the highest accuracy rate of 99.50%. At the same time, the Decision Tree (DT) and the bagging classifiers achieved the lowest processing time of 0.003 s and 0.029 s, respectively, using the GPS spoofing dataset. For the UAV location GPS spoofing dataset, the bagging classifier emerged as the top performer, achieving 99.16% accuracy and 0.002 s processing time compared to other well-known ML models. In addition, the experimental results show that our proposed methodology (RFE) outperformed other well-known ML models built on conventional feature selection techniques for detecting GPS spoofing attacks, such as mutual information gain, correlation matrices, and the chi-square test.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Network Engineering and Security, Jordan University of Science and Technology, Irbid 22110, Jordan.
- School of Computing, Queen's University, Kingston, ON K7L 3N6, Canada.
ORCID-Profile: Raghad Al-Syouf, Omar Y Aljarrah, Raed Bani-Hani, Abdallah Alma'aitah
Zitieren
APA
Al-Syouf, R., Aljarrah, O. Y., Bani-Hani, R., & Alma'aitah, A. (2025). Ensemble Machine Learning Models Utilizing a Hybrid Recursive Feature Elimination (RFE) Technique for Detecting GPS Spoofing Attacks Against Unmanned Aerial Vehicles. Sensors, 25(8), 2388. https://doi.org/10.3390/s25082388
Vancouver
Al-Syouf R, Aljarrah OY, Bani-Hani R, Alma'aitah A. Ensemble Machine Learning Models Utilizing a Hybrid Recursive Feature Elimination (RFE) Technique for Detecting GPS Spoofing Attacks Against Unmanned Aerial Vehicles. Sensors. 2025;25(8):2388. doi:10.3390/s25082388
BibTeX
@article{AlSyouf2025,
author = {Al-Syouf, Raghad and Aljarrah, Omar Y and Bani-Hani, Raed and Alma'aitah, Abdallah},
title = {Ensemble Machine Learning Models Utilizing a Hybrid Recursive Feature Elimination (RFE) Technique for Detecting GPS Spoofing Attacks Against Unmanned Aerial Vehicles},
journal = {Sensors},
year = {2025},
volume = {25},
number = {8},
pages = {2388},
doi = {10.3390/s25082388}
}
EUVIMED