A series of methods for the systematic reduction of phishing .

摘要

Phishing continues to expand as efforts to thwart attacks are ineffective and criminals behind these scams operate with apparent impunity. In order to address both issues, this research provides three steps towards the reduction of phishing: identifying phishing websites, collecting phishing evidence, and correlating the phishing incidents. The first step is to identify phishing websites automatically. Experimental results demonstrate that content-based algorithms can classify phishing websites with greater than 90% detection rates while maintaining low false-positive rates. Next, the development of custom software collects additional information and evidence about these phishing websites. In the final step, this research offers two novel algorithms to be employed as clustering metrics for phishing website content. The three steps in this research reduce phishing by blocking potential victims from the malicious content through email filters and browser-based toolbars, gathering evidence against the criminal(s) that is usable by incident investigators, and revealing relationships between phishing websites that can provide investigators with deeper knowledge of phishing activity and thus help to prioritize their apparently, limited resources.