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

2025-11-27

AI Summary

To address security threats against UAV swarm networks and the high latency, privacy leakage, model drift, and excessive computational overhead induced by resource-intensive neural networks in existing intrusion detection systems (IDS), this paper proposes a lightweight federated continual learning (FCL) IDS framework. The framework uniquely integrates federated learning with continual learning for UAV intrusion detection, enabling decentralized training that preserves data heterogeneity and privacy while supporting dynamic model updates. Leveraging a lightweight neural architecture and distributed training strategies, it significantly reduces inference latency and system resource consumption. Extensive evaluation on four benchmark datasets—UKM-IDS, UAV-IDS, TLM-UAV, and Cyber-Physical—achieves classification accuracies of 99.45%, 99.99%, 96.85%, and 98.05%, respectively, consistently outperforming conventional IDS approaches.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Humans and AI: Human-in-the-loop Machine Learning
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Responsible Web: Machine-in-the-loop, human agency and autonomy

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.

Problem

• Develops a lightweight federated IDS for UAV swarm networks
• Addresses privacy, latency, and model drift in intrusion detection
• Enables decentralized training across heterogeneous UAV data

Innovation

• Lightweight federated continuous learning-based IDS
• Decentralized training across diverse UAV swarms
• Ensures data heterogeneity and privacy preservation