Enhancement of Fake Website Detection Techniques Using Feature Selection and Filtering Algorithms
Main Article Content
Abstract
Phishing websites are malicious websites created by fraud people to mimic real websites. Phishing websites impersonates
legitimate websites to lure users into visiting the fake websites.They may lure by mailing you suspicious links that appear to be
legitimate.Phishing is a security threat to the Internet, which causes tremendous loss every year. It helps generate billions of revenue for
fraudsters. Attackers may steal user private information, credit-card and other significant financial information. In this paper , a study on
various phishing websites detection techniques such as WHOIS, Browser-Integrated Anti-phishing toolbars,attaching new top level
domains to existing blacklisted urls, feature extraction and classification based approach, a hybrid phish detection method based on
information extraction and information retrieval, CANTINA, a content-based approach, purely based on the TF-IDF(term frequency
/inverse document frequency) used in information retrieval algorithm , a novel classification method that identifies malicious web pages
based on static attributes is presented.On detailed study and analysis,it is found that there exists classification approach based on the
decision tree algorithm, which has mean absolute error of 0.292 which is comparatively larger than other algorithms, whereas its prediction
accuracy is 98.5%. Hence, improvements can be done to decrease the mean absolute error of decision tree by using feature selection and
filtering techniques to classify a revised set of attributes and design a sound and a
robust phishing detection system .
Keywords: Phishing, Detection, Techniques, Classifiers, Feature reduction, Filters, Security
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.