Fast and Accurate classification of network threats in IDS using Distributed Machine learning techniques

Gohil, Ritesh Naresh (2020) Fast and Accurate classification of network threats in IDS using Distributed Machine learning techniques. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (756kB) | Preview

Abstract

An incremental rise in the size of the data has placed a significant impact on the security of data. The advancement in Intrusion detection system can enhance the network security by monitoring and analyzing the large network data. Due to pattern recognition and abnormal behaviour detection capability of machine learning, it became very popular among the researchers to reduce the fraudulent activities. As the network system generates huge volume of data, analysing and detection of attacks in a timely manner is a challenging process. Even, after achieving the results with good accuracy using traditional machine learning approaches. This method lacks to handle large volume of data, due to the non scalable nature and limited resource capability. Therefore, an efficient, flexible and scalable solution is required for detecting multiple network attacks in a timely manner. In this work, we are proposing a distributed machine learning solution using hadoop and spark framework for anamoly based detection of network attacks. As the network attack can be classified into the multiple categories, it becomes a multi-class classification problem. In this work, we will use logistic regression, random forest and naive bayes as the classification algorithm and compare the result using both traditional and distributed approaches by utilizing the precision, recall, f1-score, training time and accuracy as the performance measures.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Dan English
Date Deposited:	26 Jan 2021 15:45
Last Modified:	26 Jan 2021 15:45
URI:	https://norma.ncirl.ie/id/eprint/4493

Actions (login required)

View Item