Authors: Ghazi Al-Naymat; Hanan Hussain; Mouhammd Al-Kasassbeh; Nidal Al-Dmour
Addresses: Artificial Intelligence Research Center (AIRC), Department of Information Technology, Ajman University, Ajman, UAE ' Department of Information Technology, Ajman University, Ajman, UAE ' Department of Computer Science, Princess Sumaya University for Technology, Amman, Jordan ' Department of Computer Engineering, Faculty of Engineering, Mutah University, Jordan
Abstract: An efficient algorithm for supporting the Intrusion Detection System is required for identifying unauthorised access that attempts to collapse a computer network's features. Machine Learning (ML) approaches like MLP and SVM Classifiers showed higher accuracy when the additional feature selection techniques are used. Another ML approach called Deep Learning (DL) algorithm does the feature selection, automatically to overcome the extra computation of feature selection. In this paper, DL method called Stacked Autoencoder (SA) is proposed for detecting known network anomalies using the SNMP-MIB data. SA transforms the set of inputs to a different set of reduced outputs (encoding). Previous outputs are decoded to get the desired output of n dimension identical to the initial input. The proposed DL method attains a high accuracy of 100% and saves the extra computations and resources spent on feature selection. The proposed model was compared with 22 ML techniques and found to outperform all other all algorithms.
Keywords: deep learning; IDS; DoS; network anomalies; SNMP-MIB.
International Journal of Computer Applications in Technology, 2021 Vol.66 No.1, pp.74 - 85
Received: 26 Jul 2020
Accepted: 18 Nov 2020
Published online: 11 Dec 2021 *