Secured Communication Schemes for UAVs in 5G: CRYSTALS-Kyber and IDS

TL;DR

This work tackles secure UAV communications in 5G by integrating a hybrid cryptographic stack that uses AES for data encryption, ECC and CRYSTALS-Kyber as key encapsulation mechanisms, and an AI-driven intrusion detection system. The architecture favors resource-constrained UAVs and evaluates performance in VPN and 5G environments, demonstrating that CRYSTALS-Kyber provides quantum resistance with modest overhead while maintaining real-time capabilities. The study includes extensive datasets for both KEM performance and IDS effectiveness, comparing multiple ML models (notably LR and XGBoost) and showing strong IDS results, including an AUC of 0.94 with XGBoost in imbalanced scenarios. Overall, the proposed framework offers a scalable, quantum-resistant security solution for UAV networks with practical implications for 5G deployments and SBC-based edge devices.

Abstract

This paper introduces a secure communication architecture for Unmanned Aerial Vehicles (UAVs) and ground stations in 5G networks, addressing critical challenges in network security. The proposed solution integrates the Advanced Encryption Standard (AES) with Elliptic Curve Cryptography (ECC) and CRYSTALS-Kyber for key encapsulation, offering a hybrid cryptographic approach. By incorporating CRYSTALS-Kyber, the framework mitigates vulnerabilities in ECC against quantum attacks, positioning it as a quantum-resistant alternative. The architecture is based on a server-client model, with UAVs functioning as clients and the ground station acting as the server. The system was rigorously evaluated in both VPN and 5G environments. Experimental results confirm that CRYSTALS-Kyber delivers strong protection against quantum threats with minimal performance overhead, making it highly suitable for UAVs with resource constraints. Moreover, the proposed architecture integrates an Artificial Intelligence (AI)-based Intrusion Detection System (IDS) to further enhance security. In performance evaluations, the IDS demonstrated strong results across multiple models with XGBoost, particularly in more demanding scenarios, outperforming other models with an accuracy of 97.33% and an AUC of 0.94. These findings underscore the potential of combining quantum-resistant encryption mechanisms with AI-driven IDS to create a robust, scalable, and secure communication framework for UAV networks, particularly within the high-performance requirements of 5G environments.

Figures (4)

• Figure 1: The Proposed System Architecture Diagram
• Figure 2: Encryption under EAX Bellare2004.
• Figure 3: The proposed data encryption algorithm.
• Figure 4: Accuracy and AUC performances for different experiments.