Content Based Phishing Detection

Authors

  • Shweta Dudhat IT Dept, SIE
  • Priyank Patel IT Dept, SIE
  • Nayan Mali Assistant Prof IT Dept, SIE

Keywords:

phishing detection, classification, data mining, security, MCAC algorithm

Abstract

Website phishing is the threatening challenge for the online society due to large number of transactions
over the internet which happens on daily bases. Phishing tries to attempt to gather sensitive information by
masquerading as a trustworthy entity in an electronic transaction/communication. The social networking sites like
Facebook, Twitter and E-mails accounts are more affected from phishing or fake pages. The main idea behind
writing this is to investigate the use of automated data mining ways in finding the complex problems of finding
phishing websites for helping the users from being hacked. The approach for data mining is called Associative
Classification method that suites best for finding phishing websites accurately. The common associative classification
algorithm MCAC: “Multi-Label Classifiers based Associative Classification” to seek its applicability to the phishing.
MCAC detects phishing websites with high accuracy than other algorithms and it generates hidden rules that other
algorithms are unable to find and has improved predictive performance.

Published

2016-05-25

How to Cite

Shweta Dudhat, Priyank Patel, & Nayan Mali. (2016). Content Based Phishing Detection. International Journal of Advance Research in Engineering, Science & Technology, 3(5), 121–126. Retrieved from https://ijarest.org/index.php/ijarest/article/view/610