An Intelligent Multi-Agent Based Anti-Phishing Scheme for Combating Internet Fraud

ABSTRACT

We present the challenges associated with the phishing and the main purpose of this paper is to develop an intelligent multi agent based anti-phishing scheme that uses a number of categorized features. Therefore, an electronic phishing detection algorithm called the SMO algorithm, which deals only with the properties of links, has been used. Weka was used in the classification process. The data is collected from various websites, e.g. Phish- Tank, Alexa. For this research, 10, 000 websites were collected.   The phishing detection system takes this data in the form of URLs. There are numerous classifiers available in Weka. In this research, the classifiers selected is the Sequential Minimal Optimization (SMO) which refers to the specific efficient optimization algorithm used inside the support vector machine (SVM) implementation.

Keywords:

Phishing, SMO, Attackers, Classification, URL, Password, Weka