Using Attribute-based Feature Selection Approaches and Machine Learning Algorithms for Detecting Fraudulent Website URLs


Aydin M., Butun I., Bicakci K., Baykal N.

10th Annual Computing and Communication Workshop and Conference (CCWC), California, United States Of America, 6 - 08 January 2020, pp.774-779 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Doi Number: 10.1109/ccwc47524.2020.9031125
  • City: California
  • Country: United States Of America
  • Page Numbers: pp.774-779
  • Keywords: Attribute-based feature selection, Cyber theft, Data analysis, Fraudulent website detection, Machine learning algorithms, INTELLIGENT PHISHING DETECTION
  • Istanbul Technical University Affiliated: No

Abstract

Phishing is a malicious form of online theft and needs to be prevented in order to increase the overall trust of the public on the Internet. In this study, for that purpose, the authors present their findings on the methods of detecting phishing websites. Data mining algorithms along with classifier algorithms are used in order to achieve a satisfactory result. In terms of classifiers, the Naive Bayes, SMO, and J48 algorithms are used. As for the feature selection algorithm; Gain Ratio Attribute and ReliefF Attribute are selected. The results are provided in a comparative way. Accordingly; SMO and J48 algorithms provided satisfactory results in the detection of phishing websites, however, Naive Bayes performed poor and is the least recommended method among all.