Phishing Website Detection using URL-Based Machine Learning for Real-Time Browser Security

Abstract: Phishing attacks have emerged as a major cybersecurity concern, where malicious websites imitate legitimate platforms to deceive users into disclosing sensitive information such as passwords, personal data, and banking credentials. Conventional detection techniques, particularly blacklist-based methods, are often ineffective against newly generated and rapidly evolving phishing URLs. To address this limitation, this paper presents a machine learning-based approach for phishing website detection using URL-based feature analysis. The proposed system focuses on extracting key lexical and structural attributes from URLs, including length, presence of abnormal characters, domain-related properties, and suspicious patterns. These features are used to train classification models such as Logistic Regression, Decision Tree, and Random Forest to distinguish between legitimate and phishing websites. The system is designed with the capability to support real-time deployment, making it suitable for integration with browser-based security mechanisms. Experimental evaluation demonstrates improved detection performance in terms of accuracy, precision, and recall. The proposed approach provides an efficient and scalable solution for enhancing user security and mitigating phishing threats in modern web environments.