Phishing Attack Detection Using Machine Learning Techniques

Teo, Yi Yang (2023) Phishing Attack Detection Using Machine Learning Techniques. Final Year Project (Bachelor), Tunku Abdul Rahman University of Management and Technology.

Text RIS_Teo Yi Yang_Fulltext.pdf Restricted to Registered users only Download (7MB)

Abstract

Today's technology is developing rapidly, due to the rapid development of technology, many people's technological knowledge cannot keep up with the pace of the times. Many attackers use deceptive emails and fake websites to conduct phishing scams. Many employees are deceived because they cannot tell the authenticity of emails. Phishers target customers of banking and online payment services such as Public Bank and Shopee. Phishing is a major cybercrime that involves attackers tricking individuals into divulging sensitive information, such as login credentials or financial data, by disguising themselves as trustworthy entity. Phishing attacks often take the form of malicious emails, which can be difficult for individuals to identify and can cause significant harm if successful. Phishing is not a new intrusion method, but its scope of harm is gradually expanding, and it has become one of the biggest threats to network security. We will create software that can detect and identify if an email or message containing might be a phishing email or containing a malicious URL by using a machine learning algorithm. The software collects a dataset from the email and trains the model to analyze the email. It helps to reduce the risk of getting scams from a phishing email. To improve the effectiveness of phishing detection, machine learning algorithms have been developed to analyze email content and identify patterns indicative of a phishing attack. In this abstract, we will discuss the use of machine learning for detecting phishing attacks, including the various algorithms and techniques that have been developed. We will also explore the challenges and limitations of using machine learning for phishing detection and provide recommendations for best practices.