Network intrusion detection sysytem using K-means Clustering and gradient boosted tree classifier

Nandini Rebello, K. Manamohan

Research output: Contribution to journalArticle

Abstract

Network intrusion detection is an important and dynamic research area because the internet is always subjected to an ever increasing number of security threats. As the type of attacks appearing is continuously changing, there is a need for developing adaptive and flexible security features. This is where anomaly-based network intrusion detection techniques are important to protect the network against malicious activities. In literature, many such intrusion detection systems have been proposed till date. In this paper, a hybrid model for intrusion detection by performing K-means clustering to form cluster models of the dataset and input it to the Gradient Boosted Tree classifier has been proposed. In order to evaluate the performance metrics the NSL-KDD dataset was used. The proposed model showed improved results having high detection rate of 99.3% and low false alarm rate of 0.19%.

Original languageEnglish
Pages (from-to)866-869
Number of pages4
JournalInternational Journal of Engineering and Advanced Technology
Volume8
Issue number3 Special Issue
Publication statusPublished - 01-02-2019
Externally publishedYes

Fingerprint

Intrusion detection
Classifiers
Internet

All Science Journal Classification (ASJC) codes

  • Environmental Engineering
  • Engineering(all)
  • Computer Science Applications

Cite this

@article{ab7fb1e7a2a44bc2bfa91da159a15739,
title = "Network intrusion detection sysytem using K-means Clustering and gradient boosted tree classifier",
abstract = "Network intrusion detection is an important and dynamic research area because the internet is always subjected to an ever increasing number of security threats. As the type of attacks appearing is continuously changing, there is a need for developing adaptive and flexible security features. This is where anomaly-based network intrusion detection techniques are important to protect the network against malicious activities. In literature, many such intrusion detection systems have been proposed till date. In this paper, a hybrid model for intrusion detection by performing K-means clustering to form cluster models of the dataset and input it to the Gradient Boosted Tree classifier has been proposed. In order to evaluate the performance metrics the NSL-KDD dataset was used. The proposed model showed improved results having high detection rate of 99.3{\%} and low false alarm rate of 0.19{\%}.",
author = "Nandini Rebello and K. Manamohan",
year = "2019",
month = "2",
day = "1",
language = "English",
volume = "8",
pages = "866--869",
journal = "International Journal of Engineering and Advanced Technology",
issn = "2249-8958",
publisher = "Blue Eyes Intelligence Engineering and Sciences Publication",
number = "3 Special Issue",

}

Network intrusion detection sysytem using K-means Clustering and gradient boosted tree classifier. / Rebello, Nandini; Manamohan, K.

In: International Journal of Engineering and Advanced Technology, Vol. 8, No. 3 Special Issue, 01.02.2019, p. 866-869.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Network intrusion detection sysytem using K-means Clustering and gradient boosted tree classifier

AU - Rebello, Nandini

AU - Manamohan, K.

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Network intrusion detection is an important and dynamic research area because the internet is always subjected to an ever increasing number of security threats. As the type of attacks appearing is continuously changing, there is a need for developing adaptive and flexible security features. This is where anomaly-based network intrusion detection techniques are important to protect the network against malicious activities. In literature, many such intrusion detection systems have been proposed till date. In this paper, a hybrid model for intrusion detection by performing K-means clustering to form cluster models of the dataset and input it to the Gradient Boosted Tree classifier has been proposed. In order to evaluate the performance metrics the NSL-KDD dataset was used. The proposed model showed improved results having high detection rate of 99.3% and low false alarm rate of 0.19%.

AB - Network intrusion detection is an important and dynamic research area because the internet is always subjected to an ever increasing number of security threats. As the type of attacks appearing is continuously changing, there is a need for developing adaptive and flexible security features. This is where anomaly-based network intrusion detection techniques are important to protect the network against malicious activities. In literature, many such intrusion detection systems have been proposed till date. In this paper, a hybrid model for intrusion detection by performing K-means clustering to form cluster models of the dataset and input it to the Gradient Boosted Tree classifier has been proposed. In order to evaluate the performance metrics the NSL-KDD dataset was used. The proposed model showed improved results having high detection rate of 99.3% and low false alarm rate of 0.19%.

UR - http://www.scopus.com/inward/record.url?scp=85073296806&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073296806&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85073296806

VL - 8

SP - 866

EP - 869

JO - International Journal of Engineering and Advanced Technology

JF - International Journal of Engineering and Advanced Technology

SN - 2249-8958

IS - 3 Special Issue

ER -