JSE_V2_N3_RP2 D. Balasubramanian R. Boopathy V. Jeyabalaraja S. Thirumal Journal on Software Engineering 2230 – 7168 2 3 6 21 phishing sites, content based approach, CANTINA Cantina is a content-based approach for detecting phishing web sites, based on the TF-IDF information retrieval algorithm. Phishing is a significant problem involving fraudulent email and web sites that trick unsuspecting users into revealing private information. In this paper discusses about the design and evaluation of several heuristics developed to reduce false positives. The experiments show that CANTINA is good at detecting phishing sites, correctly labeling approximately 95% of phishing sites using CANTINA. January - March 2008 Copyright © 2008 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=515