Fuzzy Logic for Phishing Website Detection

Abstract

Phishing is a form of fraud in which the attacker tries to lure information such as login credentials or account information by masquerading as a reputable entity or person in email, IM or other communication channels. The phishing problem is broad and no single silver-bullet solution exists to mitigate all the vulnerabilities more effectively, thus numerous techniques are often implemented to moderate specific attacks. Phishing website is the process of creating copy of legitimate website to fool the users by entering in their personal information.  Most phishing detection approaches utilizes Uniform Resource Locator (URL) blacklists or phishing website features combined with machine learning techniques to combat phishing. In this paper fuzzy logic is used for classification due to it can correctly classify individual URL, rather than others classified with training dataset. By using proper input parameters and membership function, classification becomes more accurate. More than 2000 URLs are used for classification & experimental results shows that it will give higher accuracy with less false positive rate.