Detection of Phishing Website Detection Using MLOps Approach

Abstract

In the realm of cybersecurity, the utilization of machine learning technology has emerged as a critical defense mechanism against phishing attacks, which pose a significant threat by aiming to illicitly obtain sensitive information from unsuspecting users. These attacks target vital data such as usernames, passwords, and financial details, emphasizing the need for robust detection techniques. This study delves into the application of machine learning algorithms for the identification of phishing URLs, leveraging the analysis of distinctive features present in both legitimate and malicious URLs. Our research focuses on the implementation of four key machine learning algorithms—Decision Tree, Random Forest, Support Vector Machine, and XGBoost to enhance the detection of phishing websites. The primary objective is to develop an efficient system capable of accurately identifying phishing URLs. Additionally, we have designed and deployed a user-friendly website that enables users to input URLs for real-time evaluation, distinguishing between potentially malicious and legitimate links. This platform has been deployed using Amazon Web Services, ensuring accessibility and scalability for users seeking to verify the authenticity of URLs promptly