Е-Публикации
Технически университет - София

Abstract: Unmanned Aerial Vehicles (UAVs) are at the center of a number of mission-critical applications, however, the large-scale deployment of these vehicles is accompanied by cybersecurity risks that can compromise the operational safety and data integrity. A machine learning-based network intrusion detection system implemented on UAV-GCS communications along with the UAV Network Intrusion Detection Dataset (UAV-NIDD) is what we are suggesting. Our method treats the class imbalance problem with the CRISP-DM approach, which utilizes such advanced resampling methods as Borderline-SMOTE. The ensemble voting classifier of ours combines Random Forest, Decision Tree, and XGBoost models to reach the highest possible level of detection performance. We base our approach on the UAV-NIDD Scenario 1 experimental evaluation, where our method achieves a macro-averaged F1-score of 0.95 on a 20% hold-out test set for 11 types of UAV network intrusion as the result. This research marks the first comprehensive machine learning study that used the UAV-NIDD dataset, showing the value of the systematic data science methodologies in solving cybersecurity problems and putting the spotlight on the use of UAV-specific datasets as a source of security solutions.

References

1. H. J. Hadi, Y. Cao, K. U. Nisa, A. M. Jamil, and Q. Ni,”A comprehensive survey on security, privacy issues and emerging defence technologies for UAVs,” Journal of Network and Computer Applications, vol. 213, p. 103607, 2023.
2. AL-Syouf et al.,”Machine learning approaches to intrusion detection in unmanned aerial vehicles (UAVs),” IEEE Transactions on Network Security, vol. 45, no. 3, pp. 123–140, 2024.
3. L. Zhao, S. Li, Z. Tan, A. Hawbani, S. Timotheou, and K. Yu,”A multiUAV cooperative task scheduling in dynamic environments: Throughput maximization,” IEEE Transactions on Computers, 2024.
4. M. Adil, H. Song, S. Mastorakis, H. Abulkasim, A. Farouk, and Z. Jin,”UAV-assisted IoT applications, cybersecurity threats, AI-enabled solutions, open challenges with future research directions,” IEEE Transactions on Intelligent Vehicles, vol. 9, no. 4, pp. 4583–4605, 2023.
5. M. A. Khan, N. Kumar, S. A. H. Mohsan, W. U. Khan, M. M. Nasralla, M. H. Alsharif, J. Zywiołek, and I. Ullah,”Swarm of UAVs for network management in 6G: A technical review,” IEEE Transactions on Network and Service Management, 2022.
6. H. J. Hadi, Y. Cao, S. Li, L. Xu, Y. Hu, and M. Li,”UAV-NIDD: A Dynamic Dataset for Cybersecurity and Intrusion Detection in UAV networks,” IEEE Transactions on Network Science and Engineering, 2025.
7. A. Zaman et al.,”A Systematic Machine Learning Methodology for Enhancing Accuracy and Reducing Computational Complexity in Forest Fire Detection,” Expert Systems with Applications, vol. 235, pp. 121–135, 2025.
8. D. Manivannan,”Recent endeavors in machine learning-powered intrusion detection systems for the internet of things,” Journal of Network and Computer Applications, p. 103925, 2024.
9. Haoran Liang, Jun Wu, and C. Z. J. L.,”Leveraging edge learning and game theory for intrusion detection in internet of things,” Chinese Journal on Internet of Things, vol. 5, no. 2, p. 37, 2021.
10. D. Chou and M. Jiang,”A survey on data-driven network intrusion detection,” ACM Computing Surveys (CSUR), vol. 54, no. 9, pp. 1–36, 2021.
11. S. Borra et al.,”Enhancing IoT Network Security: Machine Learning-Based Intrusion Detection Using Vortex Search Optimization and SMOTE for Improved Classification,” IEEE Access, vol. 13, pp. 234–248, 2025.
12. P. Biyyapu et al.,”Designing a modified feature aggregation model with hybrid sampling techniques for network intrusion detection,” Computer Networks, vol. 198, pp. 145–162, 2024.
13. A. Kulkarni, Y. Wang, M. Gopinath, D. Sobien, A. Rahman, and F. A. Batarseh,”A Review of Cybersecurity Incidents in the Food and Agriculture Sector,” Computers and Security, vol. 128, pp. 103–118, 2024.
14. M. A. Ferrag, L. Shu, O. Friha, X. Yang, M. Nafa, and L. Maglaras,”FELIDS: Federated learning-based intrusion detection system for agricultural Internet of Things,” Journal of Network and Computer Applications, vol. 200, pp. 103–120, 2022.
15. S. A. El Faouz, A. Souri, and N. Inanç,”LSTM-based Deep Learning Model for Cyber-attack Detection Systems in the Internet of Drones,” Computer Communications, vol. 189, pp. 78–92, 2024.
16. R. Bhuria, S. Gupta, U. Kaur, S. Bharany, A. U. Rehman, S. Hussen, G. G. Tejani, and P. Jangir,”Ensemble-based customer churn prediction in banking: a voting classifier approach for improved client retention using demographic and behavioral data,” Scientific Reports, January 14, 2025.

Issue