Approximate string matching algorithm for phishing detection

Phishing is an act of stealing personal and sensitive user information through internet and using it for financial transactions. The goal of phishers is to carry out fraudulent transactions on behalf of the victims by using the information stealed from them. Availing the services of internet has become a dangerous task to the common people with these kinds of attacks. Many methods have been developed to fight against phishing attacks. But, as the attacker uses more sophisticated techniques each method fails to perform well in detecting the attacks. Here we propose a string matching method for detecting phishing attacks, which determines the degree of similarity a URL is having with the blacklisted URLs. Thus based on the textual properties of a URL it can be classified as phishing or non-phishing. Two string matching algorithms i.e. Longest Common Subsequence (LCS) and Edit Distance are used in the hostname comparison. The accuracy rate obtained for LCS is 99.1% and for Edit Distance it is 99.5%.