PHISHING ATTACK DETECTION USING MACHINE LEARNING

Abstract

About 30 000 online applications are hacked every day, and most of the time website owners or web designers aren't even aware of what's going on with their own websites. Phishing sites are used by web hackers to deceive users and collect their private and sensitive information. Different dangers can be used by online hackers to gain access to or compromise lawful web applications. As a consequence, it's important to take the required safeguards to be aware of the threats and weaknesses that might affect the website and, as a result, the normal flow of business. The research also takes into account the creation of web application logs, which makes it easier to analyze the behavior of atypical users and identify instances where their actions are prohibited, inappropriate, or otherwise improper. The most prevalent web application dangerous threats are mitigated, and the web administrator is given detailed instructions on how to spot phishing links, a type of social engineering attack. While a number of machine learning algorithms and deep learning techniques are employed for phishing link identification, secure coding approaches are used for mitigation. The testing process's outcomes demonstrated that the website had effectively countered these risky web application assaults. The application's component that recognises phishing URLs compares several algorithms to see which one performs best. The best model results in an accuracy of 85%.