• Abdul Raheem
• Dr. Thriveni J

Phishing is still one of the most efficient ways to commit online fraud and steal credentials. In this study, we provide a real-time URL classification technique that uses a variety of signals to determine if a URL is secure or phishing. Reputation checks from reputable threat intelligence sources (URLVoid, McAfee, Sucuri), verifying the SSL certificate and WHOIS information for the domain, calculating topological features for each domain (domain age, IP blacklist), and ultimately classifying the URL using an RF classifier trained on a variety of labeled phishing datasets are all part of the classification process. We gathered a variety of data from Phishtank and OpenPhish, along with a few secure URLs, to evaluate the system's performance. to assess the system's accuracy, recall, ROC-AUC, and F1 score. We also examined how obfuscation strategies affect the evolving characteristics of phishing and how that connects to our system's overall resilience. Based on our results, we think that the capacity to identify phishing is much enhanced by combining data from several sources and feature sets as opposed to depending just on one source or feature set. As a result, this project creates a validated, practical, and efficient real-time phishing detection system. It also supports the necessity of combining various signals and offers a framework for determining which characteristics are crucial for spotting potential threats and enhancing the capabilities of a phishing detection system.

Phishing Detection, URL Classification, Threat Intelligence Aggregation, Machine Learning, Real-Time Security, LightGBM, Random Forest.

"PHISHING URL DETECTION THROUGH MULTI-SIGNAL AGGREGATION AND MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.c506-c514, January-2026, Available :http://www.jetir.org/papers/JETIR2601261.pdf

"PHISHING URL DETECTION THROUGH MULTI-SIGNAL AGGREGATION AND MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppc506-c514, January-2026, Available at : http://www.jetir.org/papers/JETIR2601261.pdf