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.
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.
The results show a success in implementing a real time, scalable, privacy-preserving, and adaptive IDS in large-scale IoT deployments through intelligent workload distribution between edge and cloud layers.
Chidera Winifred John, Eduediuyai Ekerete Dan, P. Asuquo et al.· E3S Web of Conferences· 0 citations
FedSE-1DSqueezeNet is proposed, a lightweight federated IDS tailored for resource-constrained IoT environments, designed to optimize feature extraction efficiency under strict resource constraints and achieves detection accuracy exceeding that of state-of-the-art models.
High-speed, low-latency and massive connectivity have emerged as a result of the rapid development of 5G networks, but so have security threats. Current intrusion detection tools are poorly adapted to the distributed, heterogeneous, and dynamic 5G environment where a flood of real-time information is generated over a spectrum of devices at the edges and network layers. Federated learning has been suggested in response to these threats as a new paradigm to aid in the training of intrusion detection systems without having to aggregate the information. This review provides a detailed study of intrusion detection systems in 5G networks that are federated learning-based, and how the federated learning-based intrusion detection systems can address the challenges mentioned above. The paper will also entail the discussion of the basic ideas and principles of federated learning, the importance of robust federated optimization techniques to enhance the robustness of models, and architectural design of distributed intrusion detection systems. Moreover, accuracy, efficiency, and resilience to adversarial attacks are also used as indicators of performance, which emphasizes the potential and strength of federated learning when used in complex network conditions. The key challenges and the difficulties, including the heterogeneity, communication, and security, are also discussed and analyzed. Lastly, the new trends and possible directions of research, such as the combination of AI explanations, adaptive learning, and federated learning with other emerging technologies, such as edge computing and blockchain, are also presented. In general, the paper provides a detailed and extensive perspective on the design and development of scalable and privacy-conserving and smart intrusion detection mechanisms on next-generation 5G networks.
This work presents H OME G UARD, a collaborative IDS specifically designed for the constraints and threat model of practical smart home IoT infrastructures, and rethink FL deployment by of-floading model training to gateways to manage computational heterogeneity of IoT devices and organizing anomaly detection models into device-specific communities based on privacy-preserving traffic fingerprints which do not expose sensitive data.
Philipp Eichhammer, Christian Berger, Hans P. Reiser· International Conference on...· 0 citations
An offensive-defensive system based on Deep Reinforcement Learning (DRL) algorithms is proposed, which outperform several state-of-the-art machine learning approaches in the literature, revealing that the systematic incorporation of accurate data engineering and reinforcement learning frameworks generates a field-tested security barrier that offers an expedient reaction to counteract multifaceted threats to IoT networks.
Hawraa A. Habeeb, M. Manaa· Journal of Intelligent Infor...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
