Federated Lightweight Intrusion Detection in Drone Swarms with Knowledge Distillation
Cryptography and Security
Summary
The authors focus on making drone swarms safer from cyber-attacks by creating a special security system that works without needing all data in one place. They use a method called Federated Learning combined with knowledge distillation to keep the system lightweight and efficient for drones, which have limited computing power. Testing on real devices and data showed their system accurately detects threats while saving a lot of communication and computing resources. This makes their approach a good fit for protecting drone networks in the real world.
Authors
Fawaz J. Alruwaili, Cihan Tunc
Abstract
Drone swarms are increasingly deployed in critical applications such as surveillance, disaster response, and infrastructure monitoring. However, their reliance on open communication channels and their limited computational resources make them vulnerable to a wide range of cyber-threats. There is a growing interest in intrusion detection systems (IDS) specifically designed for drone environments and operations. However, the conventional solutions including Machine Learning (ML)-based approaches require collecting all data from heterogeneous drones in the swarm and processing on a central server may not be always feasible. Federated Learning (FL) has emerged as a promising distributed solution with an additional privacy-preserving feature. Even though potential studies exist, conventional FL-based IDS frameworks still face communication and computational overhead challenges, while achieving a balance between efficiency and effective detection under practical resource constraints remains a challenge. Therefore, we propose a lightweight FL-based IDS tailored for drone swarm networks using deep neural networks (DNN) enhanced with knowledge distillation (KD) to reduce model complexity and communication costs without sacrificing detection performance. We evaluate our framework using Raspberry Pi 4 devices and a real-world drone network dataset. Our approach demonstrates a detection accuracy of approximately 98.6% while reducing overall communication cost by around 70% and computational overhead by 29%. These results show that FL combined with KD is a practical and suitable solution for secure and efficient deployment in resource-constrained drone networks.