PHISHING SPAM EMAIL ONTOLOGICAL DETECTION

Targeted Malicious Email (TME) has become more dangerous because it gathers user sensitive information. 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. Persistent threat features such as threat actor locale and weaponization tools along with recipient-oriented features such as reputation and role are leveraged with supervised data classification algorithms to demonstrate new techniques for detection of targeted malicious email. We propose a new email filtering technique using random forest classifier and Naïve Bayesian classification. A compromised router detection protocol is developed to identify congestive packet losses. We also develop feature extraction procedure to identify TME specific features. Naïve Bayesian classification is used to classify mails as either TME or trusted mail for user security avoiding frauds. A Naïve Bayesian classifier is a simple probabilistic classifier based on applying Bayesian theorem with strong (Naive) independence assumptions.