PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY

 

e-ISSN 2231-8526
ISSN 0128-7680

Home / Regular Issue / JST Vol. 26 (3) Jul. 2018 / JST-S0434-2018

 

On Evaluation of Network Intrusion Detection Systems: Statistical Analysis of CIDDS-001 Dataset Using Machine Learning Techniques

Abhishek Verma and Virender Ranga

Pertanika Journal of Science & Technology, Volume 26, Issue 3, July 2018

Keywords: Anomaly, decision tree, k-means clustering, k-nearest neighbour, labelled flow, metrics, random forests, signature

Published on: 31 Jul 2018

In this era of digital revolution, voluminous amount of data are generated from different networks on a daily basis. Security of this data is of utmost importance. Intrusion detection systems have been found to be one of the best solutions in detecting intrusions. Network intrusion detection systems are employed as a defence system to secure networks. Various techniques for the effective development of these defence systems are found in the literature. However, research on the development of datasets used for training and testing purposes of such defence systems is of equal concern. Better datasets improve the online and offline intrusion detection capabilities of detection models. Benchmark datasets like KDD 99 and NSL-KDD cup 99 are obsolete and do not contain network traces of modern attacks like Denial of Service, hence are unsuitable for the purpose of evaluation. In this study, a detailed analysis of CIDDS-001 dataset was conducted and the findings are presented. A wide range of well-known machine learning techniques were used to analyse the complexity of the dataset. Evaluation metrics including detection rate, accuracy, false positive rate, kappa statistics, and root mean squared error were utilised to assess the performance of employed machine learning techniques.

ISSN 0128-7680

e-ISSN 2231-8526

Article ID

JST-S0434-2018

Download Full Article PDF

Share this article

Recent Articles