• Duddyala Neeraja
• D.VANDANA

In today's digital landscape, websites serve a multitude of purposes, including social net-working, marketing, and information sharing. However, some websites engage in malicious or phishing activities, aiming to steal sensitive information such as financial and personal data. These phishing attempts can significantly impact users' security and privacy. Identify-ing phishing sites is a critical area of research and is essential for browsers, online applica-tions, and various digital platforms.Many approaches have been explored to detect phishing websites, with a substantial focus on text and data mining techniques. Previous studies have predominantly used text-based frameworks, relying on textual data for analysis. This research aims to investigate both text-based and feature-based classification techniques to determine the most effective model for identifying phishing websites. Specifically, the study compares different machine learning algorithms—neural networks, support vector machines, and naïve Bayes—to identify the most suitable model for phishing site predic-tion.

Phishing Websites, Text-based ,Feature based, Naïve Bayes, SVM, Neural network

"Developing an Identification-Driven Phishing Site Classifier", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 7, page no.h615-h620, July-2024, Available :http://www.jetir.org/papers/JETIR2407772.pdf

"Developing an Identification-Driven Phishing Site Classifier", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 7, page no. pph615-h620, July-2024, Available at : http://www.jetir.org/papers/JETIR2407772.pdf