phish detect: detection of phishing websites based on associative classification (ac)
Sonali Taware,Chaitrali Ghorpade,Payal Shah,Nilam Lonkar
Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology
ISSN: 2321-3337 Impact Factor:1.521 Volume:4 Issue:3 Year: 22 March,2015 Pages:384-395
Abstract
Website phishing is one of the important security challenges for the online community because of the huge numbers of online transactions performed on a daily basis. Phishing is a kind of malicious attack where cybercriminals create a fake website — meant to look like a popular online resource (a online games, online banking services or social network) and use various social engineering methods to attempt to lure users to the website .White List, Black List and the utilisation of search methods are the examples to minimize the risk of this problems. The Black List one of the popular and widely used technique into browsers, but they are less effective and unclear. Associative Classification (AC) is one of the approach based on data mining used to detect phishing websites with high accuracy. By using If-Then rules AC extracts classifiers with a high degree of predictive accuracy. Multi-label Classifier based Associative Classification (MCAC) is a developed by AC method for the problem of website phishing and to identify features that distinguish phishing websites from legitimate ones. In this paper, MCAC detects phishing websites with higher accuracy and MCAC generates new hidden rules that other algorithms are unable to find and this has improved its classifiers predictive performance.
Kewords
Classification, Data mining, websites, Phishing, Internet security.
Reference
[1] Abdelhamid, N., Ayesh, A., and Thabtah, F, “Phishing detection based Associative Classifiaction data mining”, In Expert Systems with Applications (2014).
[2]KasperskyLab (2013).
