Authors: Protić, Danijela
Stanković, Miomir 
Affiliations: Mathematical Institute of the Serbian Academy of Sciences and Arts 
Title: A hybrid model for anomaly-based intrusion detection in complex computer networks
Journal: Proceedings - 2020 21st International Arab Conference on Information Technology, ACIT 2020
First page: 9299965
Conference: 21st International Arab Conference on Information Technology, ACIT 2020; Giza; Egypt; 28 November 2020 through 30 November 2020
Issue Date: 28-Nov-2020
Rank: M33
ISBN: 9781728188553
DOI: 10.1109/ACIT50332.2020.9299965
Anomaly-based intrusion detection classifiers detect the notion of normality and classify both intrusion and/or misuse as either 'normal' or 'anomaly'. In complex computer networks, the number of the training records is often large which makes the evaluation of the classifiers computationally expensive. In this paper we present a feature selection and instances normalization algorithm that reduces the dimensionality of the dataset size, decrease processing time and increase accuracy of two classifier models, namely weighted k-Nearest Neighbor (wk-NN) and Feedforward Neural Network (FNN). The experiments are conducted on three daily records of the real computer network traffic data derived from the Kyoto 2006+ dataset. The results show high accuracy of both wk-NN and FNN classifiers but variations in mutual decisions on detected anomalies. Variations are determined with the novel hybrid model by performing logical exclusive or operation to the predicted outcomes. Improvement in the anomaly detection ranges from 0.67% to 8.08%.
Keywords: Anomaly based intrusion detection | Complex computer networks | Feedforward neural network | Weighted k-nearest neighbor
Publisher: IEEE

Show full item record


checked on Jun 14, 2024

Page view(s)

checked on May 9, 2024

Google ScholarTM




Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.