Phishing detection using classifier ensembles

This paper introduces an approach to classifying emails into phishing/non-phishing categories using the C5.0 algorithm which achieves very high precision and an ensemble of other classifiers that achieve high recall. The representation of instances used in this paper is very small consisting of only...

Full description

Saved in:
Bibliographic Details
Published in2009 eCrime Researchers Summit pp. 1 - 9
Main Authors Toolan, F., Carthy, J.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2009
Subjects
Clustering algorithms
Computer security
Credit cards
Informatics
Information security
Information technology
Internet
Laboratories
Reliability engineering
Uniform resource locators
Online AccessGet full text

Cover

More Information
Summary:This paper introduces an approach to classifying emails into phishing/non-phishing categories using the C5.0 algorithm which achieves very high precision and an ensemble of other classifiers that achieve high recall. The representation of instances used in this paper is very small consisting of only five features. Results of an evaluation of this system, using over 8,000 emails approximately half of which were phishing emails and the remainder legitimate, are presented. These results show the benefits of using this recall boosting technique over that of any individual classifier or collection of classifiers.
ISBN:1424446252
9781424446254
ISSN:2159-1237
2159-1245
DOI:10.1109/ECRIME.2009.5342607