Phishing Websites Detection Using Machine Learning

The availability of multiple services such as online banking, entertainment, education, software downloading,and social networking has accelerated the Web's evolution in recent years. As a result, a massive amount of data is constantly downloaded and transferred to the Internet. This allows attackers to access sensitive personal or financial data such as usernames, passwords, account numbers, and social security numbers. This is known as a Web phishing attack, and it is one of the most serious issues in web security. Web phishing attempts have become much more common in recent years, and phishing is now considered one of the most hazardous Web crimes, with potentially disastrous consequences for online businesses. The phisher constructs a fake or phishing website to deceive Web users and get their sensitive financial and personal information in a Web phishing attack. Phishing attacks are the most straightforward method of obtaining sensitive information from unsuspecting consumers. The goal of phishers is to obtain sensitive information such as usernames, passwords, and bank account numbers. Cyber security persons are now looking for trustworthy and steady detection techniques for phishing websites detection. By extracting and evaluating numerous aspects of authentic and phishing URLs, this project uses machine learning technology to detect phishing URLs.Phishing websites are detected using CNN LSTM & CNN Bi-LSTM, Logistic regression and XGBoost algorithms. The project's goal is to detect phishing URLs and narrow down the best machine learning algorithm by evaluating each algorithm's accuracy rate, false positive rate, and false negative rate.