Machine Learning Based Intrusion Detection Systems By Using RSC

Mallissery, Sanoop and Sathar, Shahana (2012) Machine Learning Based Intrusion Detection Systems By Using RSC. In: International Engineering Symposium (IES), April 2012, Japan.

[img] PDF
eprints_Sanoop_Japan.pdf - Published Version
Restricted to Registered users only

Download (164kB) | Request a copy


The main function of IDS (Intrusion Detection System) is to protect the system, analyze and predict the behaviors of users. These behaviors will be considered an attack or a normal behavior. Recently machine learning based Intrusion Detection systems (IDs) have been subjected to extensive researches because they can detect both misuse and anomaly. Most of existing IDs use all features in the network packet to look for known intrusive patterns. Some of these features are irrelevant or redundant. In this paper Rough Set Classification (RSC), a modern learning algorithm, is used to rank features and extracted for detecting intrusions and generate intrusion detection models. Feature ranking is a very critical step when building the model. Rough Set Theory is used to preprocess the data and reduce the dimensions. RSC creates the intrusion (decision) rules using the reducts as templates. The models generated by RSC take the form of “IF-THEN” rules, which have the advantage of explication. Finally we compared RSC with SVM, CART and ID3 using KDD 99 dataset.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: DS, Classification, Rough Set, CART,SVM, ID3
Subjects: Engineering > MIT Manipal > Information and Communication Technology
Depositing User: MIT Library
Date Deposited: 24 Feb 2015 07:18
Last Modified: 24 Feb 2015 07:18

Actions (login required)

View Item View Item