Selection of robust feature subsets for phish webpage prediction using maximum relevance and minimum redundancy criterion

Phishers usually evolve their web exploits to defeat current anti-phishing community. Accordingly, that becomes a serious web threat and puts both users and enterprises at the risks of identity theft and monetary losses day by day. In the literature, most computational efforts were dedicated to just...

Full description

Saved in:
Bibliographic Details
Main Authors: Zuhair, Hiba, Selamat, Ali Thanh, Salleh, Mazleena
Format: Article
Published: Asian Research Publishing Network (ARPN) 2015
Subjects:
Online Access:http://eprints.utm.my/id/eprint/55407/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.55407
record_format eprints
spelling my.utm.554072016-09-04T02:27:21Z http://eprints.utm.my/id/eprint/55407/ Selection of robust feature subsets for phish webpage prediction using maximum relevance and minimum redundancy criterion Zuhair, Hiba Selamat, Ali Thanh Salleh, Mazleena QA75 Electronic computers. Computer science Phishers usually evolve their web exploits to defeat current anti-phishing community. Accordingly, that becomes a serious web threat and puts both users and enterprises at the risks of identity theft and monetary losses day by day. In the literature, most computational efforts were dedicated to justify well-performed phishing detection against evolving phish exploits. However, facets like exploration of new and predictive features, selecting minimal and robust features compactness still raise as key challenges to optimize the detection scenarios over vast and strongly interrelated web. In this study, we proposed a set of new hybrid features, and refine it as few, maximum relevant, minimum redundant, and robust features as possible. In the presence of a machine learning classifier and some assessment criteria that recommended for this purpose, the reported results experimentally demonstrated that our remedial scenario could be used to optimize a phish detection model for any anti-phishing scheme in the future. Asian Research Publishing Network (ARPN) 2015-11 Article PeerReviewed Zuhair, Hiba and Selamat, Ali Thanh and Salleh, Mazleena (2015) Selection of robust feature subsets for phish webpage prediction using maximum relevance and minimum redundancy criterion. Journal of Theoretical and Applied Information Technology, 81 (2). pp. 188-205. ISSN 1992-8645
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Zuhair, Hiba
Selamat, Ali Thanh
Salleh, Mazleena
Selection of robust feature subsets for phish webpage prediction using maximum relevance and minimum redundancy criterion
description Phishers usually evolve their web exploits to defeat current anti-phishing community. Accordingly, that becomes a serious web threat and puts both users and enterprises at the risks of identity theft and monetary losses day by day. In the literature, most computational efforts were dedicated to justify well-performed phishing detection against evolving phish exploits. However, facets like exploration of new and predictive features, selecting minimal and robust features compactness still raise as key challenges to optimize the detection scenarios over vast and strongly interrelated web. In this study, we proposed a set of new hybrid features, and refine it as few, maximum relevant, minimum redundant, and robust features as possible. In the presence of a machine learning classifier and some assessment criteria that recommended for this purpose, the reported results experimentally demonstrated that our remedial scenario could be used to optimize a phish detection model for any anti-phishing scheme in the future.
format Article
author Zuhair, Hiba
Selamat, Ali Thanh
Salleh, Mazleena
author_facet Zuhair, Hiba
Selamat, Ali Thanh
Salleh, Mazleena
author_sort Zuhair, Hiba
title Selection of robust feature subsets for phish webpage prediction using maximum relevance and minimum redundancy criterion
title_short Selection of robust feature subsets for phish webpage prediction using maximum relevance and minimum redundancy criterion
title_full Selection of robust feature subsets for phish webpage prediction using maximum relevance and minimum redundancy criterion
title_fullStr Selection of robust feature subsets for phish webpage prediction using maximum relevance and minimum redundancy criterion
title_full_unstemmed Selection of robust feature subsets for phish webpage prediction using maximum relevance and minimum redundancy criterion
title_sort selection of robust feature subsets for phish webpage prediction using maximum relevance and minimum redundancy criterion
publisher Asian Research Publishing Network (ARPN)
publishDate 2015
url http://eprints.utm.my/id/eprint/55407/
_version_ 1643653787846443008
score 13.209306