Effective Lightweight Intrusion Detection in IoT Big Data Networks via Transfer Knowledge Distillation-based Federated Learning
Year: 2025
Type: book-chapter
Abstract: With the growing use of Internet of Things (IoT) devices in distributed systems, securing these networks has become a significant challenge because of their susceptibility to attacks.Intrusion detection systems have been proposed to identify attacks in IoT networks.These systems require continuous network traffic monitoring to detect anomalous behavior in realtime.Centralized systems proposed for Intrusion Detection Systems are not suitable for IoT devices due to their limited computational resources.Collaborative training of these systems leads to high overhead costs because of the devices' restricted processing power, communication limitations, and diverse large volumes of data that need to be sent to a central server.Based on federated learning, transfer learning, and knowledge distillation, we propose a lightweight IDS (FLGNKD) in this paper.In addition, to preserve privacy, a Generative Adversarial Network is utilized to generate synthetic data that mimic training data without revealing them.Furthermore, a representative sample of the distributed training data is created to address its heterogeneity.Experimental results demonstrate the proposed model's effectiveness.
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4412937893