Phishing Website Detection Using Machine Learning Algorithms

Abstract

— Phishing is a type of identity fraud that involves
carrying sensitive information including usernames, watchwords,
bank account figures, and credit card figures. People working in
the field of cyber security are now looking for reliable and
consistent phishing website detection solutions. The purpose of this
research is to apply machine learning to detect phishing URLs by
extracting and analysing different features of genuine URLs.
Decision trees, KNN, logistic regression, random forest, and
support vector machine algorithms are used to detect phishing
websites.. The goal of the study is to find the optimal machine
learning algorithm by comparing accuracy rates, false positives,
and false negatives.