An efficient feature selection based Bayesian and rough set approach for intrusion detection

Mahendra Prasad, Sachin Tripathi, Keshav Dahal

Research output: Contribution to journalArticle

Abstract

The exponential growth of network size leads to increase attacks and intrusions. Detection of these attacks from the network has turned into a noteworthy issue of security. An intrusion detection system is an important approach to achieves high detection rate. A high dimensional dataset increase complexities of detection systems. In this paper, we have designed a novel intelligent system that comprises the feature selection with a hybrid approach of the Rough set theory and the Bayes theorem. The proposed feature selection computed core features and ranked them based on estimated probability. In a decision system, an object may belong to a single or multiple decision, and a feature contains a set of objects that occurrences compute an estimated probability. The rough set theory is being applied to classify information into lower and upper approximations. Uncertain information is distinguished using rough set approximations and solved by the Bayes theorem. In this research work, it has also been highlighted the quantitative realism of recently generated dataset and compared to publicly available datasets. This approach reduces false alarm rate, computational complexity, training complexity and increases detection rate. Comparisons with relevant classifiers are also tabled that show proposed method performs better than existing classifiers.
Original languageEnglish
Article number105980
Number of pages14
JournalApplied Soft Computing
Volume87
Early online date2 Dec 2019
DOIs
Publication statusPublished - Feb 2020

Fingerprint

Rough set theory
Intrusion detection
Feature extraction
Classifiers
Intelligent systems
Computational complexity

Keywords

  • Intrusion detection system
  • CICIDS2017 dataset evaluation
  • Dataset realism
  • Feature selection
  • Rough set theory
  • Bayes theorem

Cite this

@article{4de89047ae664e29a6377c7688a27580,
title = "An efficient feature selection based Bayesian and rough set approach for intrusion detection",
abstract = "The exponential growth of network size leads to increase attacks and intrusions. Detection of these attacks from the network has turned into a noteworthy issue of security. An intrusion detection system is an important approach to achieves high detection rate. A high dimensional dataset increase complexities of detection systems. In this paper, we have designed a novel intelligent system that comprises the feature selection with a hybrid approach of the Rough set theory and the Bayes theorem. The proposed feature selection computed core features and ranked them based on estimated probability. In a decision system, an object may belong to a single or multiple decision, and a feature contains a set of objects that occurrences compute an estimated probability. The rough set theory is being applied to classify information into lower and upper approximations. Uncertain information is distinguished using rough set approximations and solved by the Bayes theorem. In this research work, it has also been highlighted the quantitative realism of recently generated dataset and compared to publicly available datasets. This approach reduces false alarm rate, computational complexity, training complexity and increases detection rate. Comparisons with relevant classifiers are also tabled that show proposed method performs better than existing classifiers.",
keywords = "Intrusion detection system, CICIDS2017 dataset evaluation, Dataset realism, Feature selection, Rough set theory, Bayes theorem",
author = "Mahendra Prasad and Sachin Tripathi and Keshav Dahal",
year = "2020",
month = "2",
doi = "10.1016/j.asoc.2019.105980",
language = "English",
volume = "87",
journal = "Applied Soft Computing",
issn = "1568-4946",
publisher = "Elsevier B.V.",

}

An efficient feature selection based Bayesian and rough set approach for intrusion detection. / Prasad, Mahendra; Tripathi, Sachin; Dahal, Keshav.

In: Applied Soft Computing, Vol. 87, 105980, 02.2020.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An efficient feature selection based Bayesian and rough set approach for intrusion detection

AU - Prasad, Mahendra

AU - Tripathi, Sachin

AU - Dahal, Keshav

PY - 2020/2

Y1 - 2020/2

N2 - The exponential growth of network size leads to increase attacks and intrusions. Detection of these attacks from the network has turned into a noteworthy issue of security. An intrusion detection system is an important approach to achieves high detection rate. A high dimensional dataset increase complexities of detection systems. In this paper, we have designed a novel intelligent system that comprises the feature selection with a hybrid approach of the Rough set theory and the Bayes theorem. The proposed feature selection computed core features and ranked them based on estimated probability. In a decision system, an object may belong to a single or multiple decision, and a feature contains a set of objects that occurrences compute an estimated probability. The rough set theory is being applied to classify information into lower and upper approximations. Uncertain information is distinguished using rough set approximations and solved by the Bayes theorem. In this research work, it has also been highlighted the quantitative realism of recently generated dataset and compared to publicly available datasets. This approach reduces false alarm rate, computational complexity, training complexity and increases detection rate. Comparisons with relevant classifiers are also tabled that show proposed method performs better than existing classifiers.

AB - The exponential growth of network size leads to increase attacks and intrusions. Detection of these attacks from the network has turned into a noteworthy issue of security. An intrusion detection system is an important approach to achieves high detection rate. A high dimensional dataset increase complexities of detection systems. In this paper, we have designed a novel intelligent system that comprises the feature selection with a hybrid approach of the Rough set theory and the Bayes theorem. The proposed feature selection computed core features and ranked them based on estimated probability. In a decision system, an object may belong to a single or multiple decision, and a feature contains a set of objects that occurrences compute an estimated probability. The rough set theory is being applied to classify information into lower and upper approximations. Uncertain information is distinguished using rough set approximations and solved by the Bayes theorem. In this research work, it has also been highlighted the quantitative realism of recently generated dataset and compared to publicly available datasets. This approach reduces false alarm rate, computational complexity, training complexity and increases detection rate. Comparisons with relevant classifiers are also tabled that show proposed method performs better than existing classifiers.

KW - Intrusion detection system

KW - CICIDS2017 dataset evaluation

KW - Dataset realism

KW - Feature selection

KW - Rough set theory

KW - Bayes theorem

U2 - 10.1016/j.asoc.2019.105980

DO - 10.1016/j.asoc.2019.105980

M3 - Article

VL - 87

JO - Applied Soft Computing

JF - Applied Soft Computing

SN - 1568-4946

M1 - 105980

ER -