Deep Learning-Based Phishing URL Detection Using Long-Term Memory (LSTM)

Abstract

With the rapid growth of online services and digital transactions, phishing attacks have emerged as a serious Cybersecurity threat, targeting users by imitating legitimate websites to steal sensitive information. This project presents a machine learning-based phishing URL detection system that aims to identify and prevent access to fraudulent websites. The proposed approach utilizes a Random Forest classifier to distinguish between phishing and legitimate URLs based on a set of extracted websites and URL features. A labeled dataset containing both genuine and malicious URL, the system analyzes its features and classifies it as either safe or phishing in real time. The experimental results demonstrate that the proposed system effectively detects phishing URLs with high accuracy, thereby enhancing user security and reducing the risk of online fraud. This approach provides a reliable and automated solution for improving Cybersecurity in web-based environments.