Unmanned aerial vehicles (UAVs) in flying ad-hoc networks (FANETs) face security challenges due to the dynamic and distributed nature of these networks. This paper presents the Federated Learning-based Intrusion Detection System (FL-IDS), an innovative approach designed to improve FANET security. FL-IDS leverages federated learning to address privacy concerns of centralized intrusion detection systems. FL-IDS operates in a decentralized manner, enabling UAVs to collaboratively train a global intrusion detection model without sharing raw data. Local models are assigned to each UAV, using client-specific data, and only updated model weights are shared with a central server. This preserves privacy while utilizing collective intelligence for effective intrusion detection. Experimental results show FL-IDS's competitive performance with Central IDS (C-IDS) while mitigating privacy concerns. The Bias Towards Specific Clients (BTSC) method further enhances FL-IDS performance, surpassing C-IDS even at lower attacker ratios. A comparative analysis with traditional intrusion detection methods, including Local IDS (L-IDS), provides insights into FL-IDS's strengths. This study significantly contributes to FANET security by introducing a privacy-aware, decentralized intrusion detection approach tailored to the unique challenges of UAV networks.

翻译：飞行自组网（FANET）中的无人机（UAV）因其动态分布式特性面临安全挑战。本文提出了基于联邦学习的入侵检测系统（FL-IDS），这是一种旨在提升FANET安全性的创新方法。FL-IDS利用联邦学习解决集中式入侵检测系统的隐私问题。该系统以去中心化方式运行，使无人机能够在不共享原始数据的情况下协作训练全局入侵检测模型。每架无人机分配使用客户端特定数据的本地模型，仅将更新后的模型权重共享给中央服务器。这在利用集体智慧进行有效入侵检测的同时保护了隐私。实验结果表明，FL-IDS在缓解隐私问题的同时，性能与集中式入侵检测系统（C-IDS）相当。针对特定客户端的偏差方法（BTSC）进一步提升了FL-IDS的性能，即使在较低攻击者比例下也超越了C-IDS。通过与包括本地入侵检测系统（L-IDS）在内的传统入侵检测方法进行对比分析，揭示了FL-IDS的优势。本研究通过引入一种适应无人机网络独特挑战的隐私感知、去中心化入侵检测方法，为FANET安全做出了重要贡献。