Belavagi, Manjula C and Muniyal, Balachandra (2017) Multi Class Machine Learning Algorithms forIntrusion Detection - A Performance Study. Communications in Computer and Information Science (Information Processing and Management). ISSN 1865-0929
![]() |
PDF
3445.pdf - Published Version Restricted to Registered users only Download (199kB) | Request a copy |
Abstract
Advancement of the network technology has increased our dependency on the Internet. Hence the security of the network plays avery important role. The network intrusions can be identi�ed using In-trusion Detection System (IDS). Machine learning algorithms are usedto predict the network behavior as intrusion or normal. This paper dis- cusses the prediction analysis of di�erent supervised machine learningalgorithms namely Logistic Regression, Gaussian Naive Bayes, SupportVector Machine and Random Forest on NSL-KDD dataset. These ma-chine learning classi�cation techniques are used to predict the four dif- ferent types of attacks namely Denial of Service attack, Remote to Local(R2L), Probe and User to Root(U2R) attacks using multi-class classi�-cation technique.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Intrusion Detection, Machine Learning, Network Security |
Subjects: | Engineering > MIT Manipal > Information and Communication Technology |
Depositing User: | MIT Library |
Date Deposited: | 18 Nov 2017 08:28 |
Last Modified: | 18 Nov 2017 08:28 |
URI: | http://eprints.manipal.edu/id/eprint/149984 |
Actions (login required)
![]() |
View Item |