PhishOFE: A Novel Machine Learning Framework for Real-Time Phishing URL Detection with Optimized Feature Engineering

With the rapid expansion of the internet and the growing sophistication of cyber threats, phishing attacks have become a serious cybersecurity challenge for individuals and organizations. Phishing attacks, primarily executed through deceptive URLs, aim to mislead users into providing sensitive information, leading to financial loss, identity theft, and security breaches. The increasing complexity of phishing techniques necessitates the development of robust and intelligent detection frameworks. This paper introduces PhishOFE, a novel machine learning-based framework for phishing URL detection that utilizes Optimized Feature Engineering. The proposed framework extracts URL and HTML-based features and derives composite features to enhance phishing detection accuracy while minimizing dependence on thirdparty data. The PhishOFE dataset is constructed using diverse phishing and legitimate URLs sourced from various repositories, which ensures comprehensive feature representation. Experiments were conducted using ten different machine learning models, and the results show that CatBoost achieves the highest detection accuracy of 99.48%, with superior precision, recall, and F1-score. The framework reduces computational complexity by utilizing an existing machine learning model, making it suitable for real-time applications and its potential for integration into cybersecurity solutions to counter evolving phishing tactics.