Logo image
B-APT: Bayesian Anti-Phishing Toolbar
Conference proceeding

B-APT: Bayesian Anti-Phishing Toolbar

P Likarish, Eunjin Jung, D Dunbar, T.E Hansen and J.P Hourcade
2008 IEEE International Conference on Communications, pp.1745-1749
05/2008
DOI: 10.1109/ICC.2008.335

View Online

Abstract

Identity theft is one of the fastest growing crimes in the nation, and phishing has been a primary tool used for this type of theft. In this paper, we present B-APT, a Bayesian anti-phishing toolbar designed to help users identify phishing Websites and protect their sensitive information. Bayesian filters have shown great performance in content-based spam filtering and we adapt a Bayesian filter to detect phishing attacks in the Web browser. The experimental results show that our toolbar effectively detects phishing sites, and is also efficient in terms of page load delay. Among the phishing sites in our testbed, B-APT detected 100% of phishing sites while IE and Firefox only detected 64% and 55%, respectively. Netcraft and SpoofGuard show better accuracy, 98% and 90%, respectively.
Bayesian methods Cities and towns Computer science Delay effects Information filtering Information filters Internet Protection Testing Uniform resource locators

Details

Logo image