• Asha R
• Bhoomika K Shetty
• Chaitra S Moger
• H G Rakshitha
• Prof. Shana Santhosh

Phishing remains a prevalent and evolving cyber threat, designed to trick others into disclosing private information. This essay presents PHISHNET, a comprehensive threat intelligence system that leverages machine learning to detect phishing attacks across multiple vectors, including URLs, emails, and SMS messages. The system employs a rich feature set, including the extraction of 30 distinct URL characteristics, alongside natural language processing (NLP) for email and SMS content analysis. We utilize algorithms such as Gradient Boosting for URL classification and Random Forest for email and SMS spam/phishing identification. PHISHNET integrates these detection mechanisms into a unified platform, offering real-time analysis and proactive defense. Experimental results demonstrate high efficacy, with URL detection achieving 98% accuracy, email detection 97%, and SMS detection 96%. This work contributes to building resilient defenses against sophisticated phishing attacks, thereby enhancing trust in digital communication channels.

Phishing Detection, Machine Learning, Threat Intelligence, URL Analysis, Email Security, SMS Security, Gradient Boosting, Random Forest, Natural Language Processing.

"PHISHNET: A Machine Learning-Powered Threat Intelligence System for Multi-Vector Phishing Attack Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.460-463, July-2025, Available :http://www.jetir.org/papers/JETIRGX06086.pdf

"PHISHNET: A Machine Learning-Powered Threat Intelligence System for Multi-Vector Phishing Attack Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp460-463, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06086.pdf