Implementation of Machine Learning to Automate the Phishing Websites Detection

Abstract

The number of gadgets linked to the internet has increased dramatically in recent years. In comparison to other types of cyber-attacks, phishing has become the most popular in cyberspace because it leverages human flaws rather than technology vulnerabilities. In phishing assault, an internet user is duped into providing personal information, such as login credentials or credit card information, by an apparently trustworthy organization. Many researchers have recently proposed alternative ways to phishing assaults. However, they are still reliant on user engagement to progress. Therefore, this research aims at studying on how Machine learning may be used to automate the identification of phishing websites. This research will use the stratified sampling method which is applied for 150 users raging from normal users, organizations’ IT team, as well as the browser team by distributing the Online Survey. In addition, three random participants are selected to attend the interview session to validate the reliability of the online survey result. At the end of this research, an automatic detection tool is developed to achieve the aim. Furthermore, this research motivates the future work in terms of adding more functional features and also the available platforms.