A competitive three-level pruning technique for information security

Morshed Chowdhury, Jemal Abawajy, Andrei Kelarev, Kouichi Sakurai

Research output: Contribution to journalArticle

Abstract

The reduction of size of ensemble classifiers is important for various security applications. The majority of known pruning algorithms belong to the following three categories: ranking based, clustering based, and optimization based methods. The present paper introduces and investigates a new pruning technique. It is called a Three-Level Pruning Technique, TLPT, because it simultaneously combines all three approaches in three levels of the process. This paper investigates the TLPT method combining the state-of-the-art ranking of the Ensemble Pruning via Individual Contribution ordering, EPIC, the clustering of the K-Means Pruning, KMP, and the optimisation method of Directed Hill Climbing Ensemble Pruning, DHCEP, for a phishing dataset. Our new experiments presented in this paper show that the TLPT is competitive in comparison to EPIC, KMP and DHCEP, and can achieve better outcomes. These experimental results demonstrate the effectiveness of the TLPT technique in this example of information security application.

Original languageEnglish
Pages (from-to)25-32
Number of pages8
JournalCommunications in Computer and Information Science
Volume490
DOIs
Publication statusPublished - Jan 1 2014

Fingerprint

Information Security
Security of data
Pruning
Classifiers
Ranking
Ensemble
Clustering
Ensemble Classifier
Hill Climbing
Experiments
K-means
Optimization Methods
Optimization
Experimental Results
Demonstrate
Experiment
Local search (optimization)

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Mathematics(all)

Cite this

A competitive three-level pruning technique for information security. / Chowdhury, Morshed; Abawajy, Jemal; Kelarev, Andrei; Sakurai, Kouichi.

In: Communications in Computer and Information Science, Vol. 490, 01.01.2014, p. 25-32.

Research output: Contribution to journalArticle

Chowdhury, Morshed ; Abawajy, Jemal ; Kelarev, Andrei ; Sakurai, Kouichi. / A competitive three-level pruning technique for information security. In: Communications in Computer and Information Science. 2014 ; Vol. 490. pp. 25-32.
@article{64e897b270bb4935aa57de33b222f1ff,
title = "A competitive three-level pruning technique for information security",
abstract = "The reduction of size of ensemble classifiers is important for various security applications. The majority of known pruning algorithms belong to the following three categories: ranking based, clustering based, and optimization based methods. The present paper introduces and investigates a new pruning technique. It is called a Three-Level Pruning Technique, TLPT, because it simultaneously combines all three approaches in three levels of the process. This paper investigates the TLPT method combining the state-of-the-art ranking of the Ensemble Pruning via Individual Contribution ordering, EPIC, the clustering of the K-Means Pruning, KMP, and the optimisation method of Directed Hill Climbing Ensemble Pruning, DHCEP, for a phishing dataset. Our new experiments presented in this paper show that the TLPT is competitive in comparison to EPIC, KMP and DHCEP, and can achieve better outcomes. These experimental results demonstrate the effectiveness of the TLPT technique in this example of information security application.",
author = "Morshed Chowdhury and Jemal Abawajy and Andrei Kelarev and Kouichi Sakurai",
year = "2014",
month = "1",
day = "1",
doi = "10.1007/978-3-662-45670-5",
language = "English",
volume = "490",
pages = "25--32",
journal = "Communications in Computer and Information Science",
issn = "1865-0929",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - A competitive three-level pruning technique for information security

AU - Chowdhury, Morshed

AU - Abawajy, Jemal

AU - Kelarev, Andrei

AU - Sakurai, Kouichi

PY - 2014/1/1

Y1 - 2014/1/1

N2 - The reduction of size of ensemble classifiers is important for various security applications. The majority of known pruning algorithms belong to the following three categories: ranking based, clustering based, and optimization based methods. The present paper introduces and investigates a new pruning technique. It is called a Three-Level Pruning Technique, TLPT, because it simultaneously combines all three approaches in three levels of the process. This paper investigates the TLPT method combining the state-of-the-art ranking of the Ensemble Pruning via Individual Contribution ordering, EPIC, the clustering of the K-Means Pruning, KMP, and the optimisation method of Directed Hill Climbing Ensemble Pruning, DHCEP, for a phishing dataset. Our new experiments presented in this paper show that the TLPT is competitive in comparison to EPIC, KMP and DHCEP, and can achieve better outcomes. These experimental results demonstrate the effectiveness of the TLPT technique in this example of information security application.

AB - The reduction of size of ensemble classifiers is important for various security applications. The majority of known pruning algorithms belong to the following three categories: ranking based, clustering based, and optimization based methods. The present paper introduces and investigates a new pruning technique. It is called a Three-Level Pruning Technique, TLPT, because it simultaneously combines all three approaches in three levels of the process. This paper investigates the TLPT method combining the state-of-the-art ranking of the Ensemble Pruning via Individual Contribution ordering, EPIC, the clustering of the K-Means Pruning, KMP, and the optimisation method of Directed Hill Climbing Ensemble Pruning, DHCEP, for a phishing dataset. Our new experiments presented in this paper show that the TLPT is competitive in comparison to EPIC, KMP and DHCEP, and can achieve better outcomes. These experimental results demonstrate the effectiveness of the TLPT technique in this example of information security application.

UR - http://www.scopus.com/inward/record.url?scp=84911888051&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911888051&partnerID=8YFLogxK

U2 - 10.1007/978-3-662-45670-5

DO - 10.1007/978-3-662-45670-5

M3 - Article

AN - SCOPUS:84911888051

VL - 490

SP - 25

EP - 32

JO - Communications in Computer and Information Science

JF - Communications in Computer and Information Science

SN - 1865-0929

ER -