Skip to main content

Research Repository

Advanced Search

Memory efficient federated deep learning for intrusion detection in IoT networks.

Zakariyya, Idris; Kalutarage, Harsha; Al-Kadri, M. Omar

Authors

M. Omar Al-Kadri



Contributors

Sadiq Sani
Editor

Abstract

Deep Neural Networks (DNNs) methods are widely proposed for cyber security monitoring. However, training DNNs requires a lot of computational resources. This restricts direct deployment of DNNs to resource-constrained environments like the Internet of Things (IoT), especially in federated learning settings that train an algorithm across multiple decentralized edge devices. Therefore, this paper proposes a memory efficient method of training a Fully Connected Neural Network (FCNN) for IoT security monitoring in federated learning settings. The model‘s performance was evaluated against eleven realistic IoT benchmark datasets. Experimental results show that the proposed method can reduce memory requirement by up to 99.46 percentage points when compared to its benchmark counterpart, while maintaining the state-of-the-art accuracy and F1 score.

Citation

ZAKARIYYA, A. KALUTARAGE, H. and AL-KADRI, M.O. 2021. Memory efficient federated deep learning for intrusion detection in IoT networks. In Sani, S. and Kalutarage, H. (eds.) AI and cybersecurity 2021 (AI-Cybersec 2021): proceedings of the Workshop on AI and Cybersecurity (AI-Cybersec 2021) co-located with 41st (British Computer Society's Specialist Group on Artificial Intelligence) SGAI international conference on artificial intelligence (SGAI 2021): [virtual conference]. Aachen: CEUR Workshop Proceedings [online], 3125, pages 85-99. Available from: http://ceur-ws.org/Vol-3125/paper7.pdf

Conference Name 2021 Workshop on AI and cybersecurit (AI-Cybersec 2021), co-located with 41st (British Computer Society's Specialist Group on Artificial Intelligence) SGAI international conference on artificial intelligence (SGAI 2021)
Conference Location Cambridge, UK
Start Date Dec 14, 2021
Acceptance Date Nov 21, 2021
Online Publication Date Dec 14, 2021
Publication Date Apr 17, 2022
Deposit Date May 6, 2022
Publicly Available Date May 6, 2022
Publisher CEUR Workshop Proceedings
Pages 85-99
Series Title CEUR workshop proceedings
Series Number 3125
Series ISSN 1613-0073
Book Title AI and cybersecurity 2021 (AI-Cybersec 2021): proceedings of the Workshop on AI and Cybersecurity (AI-Cybersec 2021) co-located with 41st (British Computer Society's Specialist Group on Artificial Intelligence) SGAI international conference on artificial
Keywords Deep neural networks (DNNs); Internet of Things (IoT); Fully connected neural network (FCNN); Memory; Federated learning; Intrusion detection
Public URL https://rgu-repository.worktribe.com/output/1654366
Publisher URL http://ceur-ws.org/Vol-3125/

Files





You might also like



Downloadable Citations