Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

An intrusion detection system based on deep belief networks

Belarbi, Othmane ORCID:, Khan, Aftab, Carnelli, Pietro and Spyridopoulos, Theodoros ORCID: 2022. An intrusion detection system based on deep belief networks. Presented at: 4th International Conference on Science of Cyber Security - SciSec 2022, Matsue city, Shimane, Japan, 10-12 August 2022. Lecture Notes in Computer Science. Springer, pp. 377-392. 10.1007/978-3-031-17551-0_25

[thumbnail of IDSDBN.pdf]
PDF - Accepted Post-Print Version
Download (718kB) | Preview


The rapid growth of connected devices has led to the proliferation of novel cyber-security threats known as zero-day attacks. Traditional behaviour-based Intrusion Detection Systems (IDSs) rely on Deep Neural Networks (DNNs) to detect these attacks. The quality of the dataset used to train the DNNs plays a critical role in the detection performance, with underrepresented samples causing poor performances. In this paper, we develop and evaluate the performance of Deep Belief Networks (DBNs) on detecting cyber-attacks within a network of connected devices. The CICIDS2017 dataset was used to train and evaluate the performance of our proposed DBN approach. Several class balancing techniques were applied and evaluated. Lastly, we compare our approach against a conventional Multi-Layer Perceptron (MLP) model and the existing state-of-the-art. Our proposed DBN approach shows competitive and promising results, with significant performance improvement on the detection of attacks underrepresented in the training dataset.

Item Type: Conference or Workshop Item (Paper)
Date Type: Published Online
Status: Published
Schools: Computer Science & Informatics
Publisher: Springer
ISBN: 978-3-031-17550-3
ISSN: 0302-9743
Date of First Compliant Deposit: 27 October 2022
Date of Acceptance: 28 June 2022
Last Modified: 11 Nov 2022 11:53

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics