Nurzhaubayeva G., Dashtifard N., Yedilkhan D., Mahmoud H., Cebecioglu B. B., De Mi
A lightweight machine learning based physical layer authentication design for UAV communications // Proceedings of the 2025 IEEE European Technology and Engineering Management Summit (E-TEMS). — 2025. — Conference held 26–28 May 2025. — DOI: 10.1109/E-TEMS64751.2025.11239238.

Abstract: The rapid development of UAV-enabled wireless networks introduces significant security vulnerabilities that require robust authentication mechanisms. This paper proposes a physical layer authentication (PLA) framework leveraging machine learning techniques to improve security and threat detection in UAV communications. The approach integrates Support Vector Machine (SVM) classification with traditional PLA methods to identify and mitigate attacks in real time. The framework exploits wireless channel characteristics and signal properties to establish reliable authentication protocols. Experimental results show that the proposed system achieves up to 97% detection accuracy across various attack scenarios, including eavesdropping and spoofing, while maintaining low computational overhead. The results demonstrate the effectiveness of the approach in enhancing UAV communication security and highlight its suitability for real-time, resource-constrained aerial networks.

Link / DOI: https://doi.org/10.1109/E-TEMS64751.2025.11239238