Detecting Phishing Emails Using Random Forest and AdaBoost Classifier Model

Abstract

Phishing attack occurs when a phishing email which is a legitimate-looking email, designed to lure the recipient into believing that it is a genuine email to open and click malicious links embedded into the email. This leads to user reveal sensitive information such as credit card number, usernames or passwords to the attacker thereby gaining entry into the compromised account. Online surveys have put phishing attack as the leading attack for web content mostly targeting financial institutions. According to a survey conducted by Ponemon Institute LLC 2017, the loss due to phishing attack is about $1.5 billion per year. This is a global threat to information security and it’s on the rise due to IoT (Internet of Things) and thus requires a better phishing detection mechanism to mitigate these loses and reputation injury. This research paper explores and reports the use of a combination of machine learning algorithms; Random Forest and AdaBoost and use of more phishing email features in improving the accuracy of phishing detection and prevention. This project will explore the existing phishing methods, investigate the effect of combining two machine learning algorithms to detect and prevent phishing attacks, design and develop a supervised classifier which can detect phishing and prevent phishing emails and test the model with existing data. A dataset consisting of both benign and phishing emails will be used to conduct a supervised learning by the model. Expected accuracy is 99.9%, False Negative (FN) and False Positive (FP) rates of 0.1% and below.