Detecting Targeted Malicious Email by Spam Filtering Using Naïve Bayesian Classification

Abstract: In recent years, Targeted Malicious Email (TME) has become more dangerous. Beyond spam and phishing designed to trick users into revealing information, TME exploits computer networks and gathers sensitive information. It targets on single users and is designed to appear legitimate and trustworthy. In this paper, we propose a new email filtering technique using random forest classifier. A compromised router detection protocol is developed to identify congestive packet losses. We also develop feature extraction procedure to identify TME specific features. Naive Bayesian classification is used to classify mails as either TME or trusted mail.

Keywords: Targeted Malicious Email, router detection protocol, feature extraction, Naive Bayesian.