International Journal of Scientific Research and Engineering Development

Phishing attacks remain one of the most pervasive cybersecurity threats, with the FBI's Internet Crime Complaint Centre reporting over 880,000 complaints and losses exceeding $12.5 billion in 2023 alone. This paper presents a comprehensive AI-based phishing URL detection system that combines machine learning classification with multi-source domain intelligence signals. The proposed system integrates four key analytical components: ML-based classification using ensemble methods, WHOIS domain analysis for registration intelligence, SSL certificate inspection for cryptographic validation, IP address geolocation and reputation analysis, and a unified risk scoring mechanism. By synthesizing these diverse data sources, the system achieves robust detection capabilities that address the limitations of traditional blacklist-based approaches and single-method detection systems. We evaluate the system's architecture, feature engineering methodology, and performance characteristics, demonstrating how multi-source intelligence fusion enables accurate, real-time phishing detection with low false positive rates.

Selvamani C, J.Savitha, "AI-Based Phishing URL Detection System: A Multi-Source Intelligence Approach with Machine Learning Classification" International Journal of Scientific Research and Engineering Development, V9(2): Page(97-104) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.