An Efficient Intrusion Detection Approach Utilizing Various WEKA Classifiers

Abstract

Detection of Intrusion is an essential expertise business segment as well as a dynamic area of study and expansion caused by its requirement. Modern day intrusion detection systems still have these limitations of time sensitivity. The main requirement is to develop a system which is able of handling large volume of network data to detect attacks more accurately and proactively. Research conducted by on the KDDCUP99 dataset resulted in a various set of attributes for each of the four major attack types. Without reducing the number of features, detecting attack patterns within the data is more difficult for rule generation, forecasting, or classification. The goal of this research is to present a new method that Compare results of appropriately categorized and inaccurately categorized as proportions and the features chosen. In this research paper we explained our approach “An Efficient Intrusion Detection Approach Utilizing Various WEKA Classifiers” which is proposed to enhance the competence of recognition of intrusion employing different WEKA classifiers on processed KDDCUP99 dataset. During the experiment we employed Adaboost, J48, JRip, NaiveBayes and Random Tree classifiers to categorize the different attacks from the processed KDDCUP99.

Keywords: Classifier, Data Mining, IDS, Network Security, Attacks, Cyber Security