Effective Lightweight Intrusion Detection in IoT Big Data Networks via Transfer Knowledge Distillation-based Federated Learning

DOI

10.2991/978-94-6463-805-9_18How to use a DOI?

Keywords

Federated learning; Knowledge distillation; Generative models; Non IID data

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 real-time. 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.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Imene Bouleghlimat
AU  - Souheila Boudouda
AU  - Safia Bouleghlimat
PY  - 2025
DA  - 2025/08/05
TI  - Effective Lightweight Intrusion Detection in IoT Big Data Networks via Transfer Knowledge Distillation-based Federated Learning
BT  - Proceedings of the First International Conference on Artificial Intelligence, Smart Technologies and Communications (AISTC 2025)
PB  - Atlantis Press
SP  - 156
EP  - 164
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-805-9_18
DO  - 10.2991/978-94-6463-805-9_18
ID  - Bouleghlimat2025
ER  -