A predictive model for network intrusion detection using stacking approach

Smitha Rajagopal, Poornima Panduranga Kundapur, K. S. Hareesha

Research output: Contribution to journalArticle

Abstract

Due to the emerging technological advances, cyber-attacks continue to hamper information systems. The changing dimensionality of cyber threat landscape compel security experts to devise novel approaches to address the problem of network intrusion detection. Machine learning algorithms are extensively used to detect intrusions by dint of their remarkable predictive power. This work presents an ensemble approach for network intrusion detection using a concept called Stacking. As per the popular no free lunch theorem of machine learning, employing single classifier for a problem at hand may not be ideal to achieve generalization. Therefore, the proposed work on network intrusion detection emphasizes upon a combinative approach to improve performance. A robust processing paradigm called Graphlab Create, capable of upholding massive data has been used to implement the proposed methodology. Two benchmark datasets like UNSW NB-15 and UGR' 16 datasets are considered to demonstrate the validity of predictions. Empirical investigation has illustrated that the performance of the proposed approach has been reasonably good. The contribution of the proposed approach lies in its finesse to generate fewer misclassifications pertaining to various attack vectors considered in the study.

Original languageEnglish
Pages (from-to)2734-2741
Number of pages8
JournalInternational Journal of Electrical and Computer Engineering
Volume10
Issue number3
DOIs
Publication statusPublished - 01-01-2019

Fingerprint

Intrusion detection
Learning systems
Learning algorithms
Information systems
Classifiers
Processing

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Electrical and Electronic Engineering

Cite this

@article{035968235e664017946a95dae29ac504,
title = "A predictive model for network intrusion detection using stacking approach",
abstract = "Due to the emerging technological advances, cyber-attacks continue to hamper information systems. The changing dimensionality of cyber threat landscape compel security experts to devise novel approaches to address the problem of network intrusion detection. Machine learning algorithms are extensively used to detect intrusions by dint of their remarkable predictive power. This work presents an ensemble approach for network intrusion detection using a concept called Stacking. As per the popular no free lunch theorem of machine learning, employing single classifier for a problem at hand may not be ideal to achieve generalization. Therefore, the proposed work on network intrusion detection emphasizes upon a combinative approach to improve performance. A robust processing paradigm called Graphlab Create, capable of upholding massive data has been used to implement the proposed methodology. Two benchmark datasets like UNSW NB-15 and UGR' 16 datasets are considered to demonstrate the validity of predictions. Empirical investigation has illustrated that the performance of the proposed approach has been reasonably good. The contribution of the proposed approach lies in its finesse to generate fewer misclassifications pertaining to various attack vectors considered in the study.",
author = "Smitha Rajagopal and Kundapur, {Poornima Panduranga} and Hareesha, {K. S.}",
year = "2019",
month = "1",
day = "1",
doi = "10.11591/ijece.v10i3.pp2734-2741",
language = "English",
volume = "10",
pages = "2734--2741",
journal = "International Journal of Electrical and Computer Engineering",
issn = "2088-8708",
publisher = "Institute of Advanced Engineering and Science (IAES)",
number = "3",

}

A predictive model for network intrusion detection using stacking approach. / Rajagopal, Smitha; Kundapur, Poornima Panduranga; Hareesha, K. S.

In: International Journal of Electrical and Computer Engineering, Vol. 10, No. 3, 01.01.2019, p. 2734-2741.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A predictive model for network intrusion detection using stacking approach

AU - Rajagopal, Smitha

AU - Kundapur, Poornima Panduranga

AU - Hareesha, K. S.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Due to the emerging technological advances, cyber-attacks continue to hamper information systems. The changing dimensionality of cyber threat landscape compel security experts to devise novel approaches to address the problem of network intrusion detection. Machine learning algorithms are extensively used to detect intrusions by dint of their remarkable predictive power. This work presents an ensemble approach for network intrusion detection using a concept called Stacking. As per the popular no free lunch theorem of machine learning, employing single classifier for a problem at hand may not be ideal to achieve generalization. Therefore, the proposed work on network intrusion detection emphasizes upon a combinative approach to improve performance. A robust processing paradigm called Graphlab Create, capable of upholding massive data has been used to implement the proposed methodology. Two benchmark datasets like UNSW NB-15 and UGR' 16 datasets are considered to demonstrate the validity of predictions. Empirical investigation has illustrated that the performance of the proposed approach has been reasonably good. The contribution of the proposed approach lies in its finesse to generate fewer misclassifications pertaining to various attack vectors considered in the study.

AB - Due to the emerging technological advances, cyber-attacks continue to hamper information systems. The changing dimensionality of cyber threat landscape compel security experts to devise novel approaches to address the problem of network intrusion detection. Machine learning algorithms are extensively used to detect intrusions by dint of their remarkable predictive power. This work presents an ensemble approach for network intrusion detection using a concept called Stacking. As per the popular no free lunch theorem of machine learning, employing single classifier for a problem at hand may not be ideal to achieve generalization. Therefore, the proposed work on network intrusion detection emphasizes upon a combinative approach to improve performance. A robust processing paradigm called Graphlab Create, capable of upholding massive data has been used to implement the proposed methodology. Two benchmark datasets like UNSW NB-15 and UGR' 16 datasets are considered to demonstrate the validity of predictions. Empirical investigation has illustrated that the performance of the proposed approach has been reasonably good. The contribution of the proposed approach lies in its finesse to generate fewer misclassifications pertaining to various attack vectors considered in the study.

UR - http://www.scopus.com/inward/record.url?scp=85077908261&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077908261&partnerID=8YFLogxK

U2 - 10.11591/ijece.v10i3.pp2734-2741

DO - 10.11591/ijece.v10i3.pp2734-2741

M3 - Article

AN - SCOPUS:85077908261

VL - 10

SP - 2734

EP - 2741

JO - International Journal of Electrical and Computer Engineering

JF - International Journal of Electrical and Computer Engineering

SN - 2088-8708

IS - 3

ER -