An Efficient Privacy-preserving Intrusion Detection Scheme for UAV Swarm Networks

TL;DR

This paper introduces a lightweight, federated, continuous learning-based intrusion detection system for UAV swarms that enhances security while preserving privacy and reducing latency.

Contribution

It proposes a novel federated learning approach for UAV swarm IDS, addressing privacy, latency, and model drift issues in existing systems.

Findings

Achieved over 99% classification accuracy on multiple datasets.

Reduced latency and privacy risks compared to traditional IDS.

Demonstrated robustness against diverse security attacks.

Abstract

The rapid proliferation of unmanned aerial vehicles (UAVs) and their applications in diverse domains, such as surveillance, disaster management, agriculture, and defense, have revolutionized modern technology. While the potential benefits of swarm-based UAV networks are growing significantly, they are vulnerable to various security attacks that can jeopardize the overall mission success by degrading their performance, disrupting decision-making, and compromising the trajectory planning process. The Intrusion Detection System (IDS) plays a vital role in identifying potential security attacks to ensure the secure operation of UAV swarm networks. However, conventional IDS primarily focuses on binary classification with resource-intensive neural networks and faces challenges, including latency, privacy breaches, increased performance overhead, and model drift. This research aims to address these challenges by developing a novel lightweight and federated continuous learning-based IDS scheme. Our proposed model facilitates decentralized training across diverse UAV swarms to ensure data heterogeneity and privacy. The performance evaluation of our model demonstrates significant improvements, with classification accuracies of 99.45% on UKM-IDS, 99.99% on UAV-IDS, 96.85% on TLM-UAV dataset, and 98.05% on Cyber-Physical datasets.