Enhancing Phishing E-Mail Classifiers: A Lexical URL Analysis Approach

Abstract

This is a study that focuses on enhancing the mitiga-tion of bulk phishing email messages (i.e. email mes-sages with generic socially engineered content that tar-get a broad range of recipients). This study is based on a phishing website detection technique that we have proposed previously. The previously proposed tech-nique was able to achieve 97% of classification accu-racy of phishing websites by lexically analyzing their URLs. The centre claim of this study is that the classi-fication accuracy of anti-phishing email filters enhance when they incorporate the proposed lexical URL analy-sis technique. To evaluate the claims, a highly accurate anti-phishing email classifier is constructed and tested against publicly available phishing and legitimate email data sets.