CANTINA+
Abstract
Phishing is a plague in cyberspace. Typically, phish detection methods either use human-verified URL blacklists or exploit Web page features via machine learning techniques. However, the former is frail in terms of new phish, and the latter suffers from the scarcity of effective features and the high false positive rate (FP). To alleviate those problems, we propose a layered anti-phishing solution that aims at (1) exploiting the expressiveness of a rich set of features with machine learning to achieve a high true positive rate (TP) on novel phish, and (2) limiting the FP to a low level via filtering algorithms.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Sep 01, 2011
- Source ID
- 10.1145/2019599.2019606
Entities
People
- Carolyn P. Rose
- Guang Xiang
- Jason Hong
- Lorrie Cranor
Organizations
- Army Research Office
- Carnegie Mellon University
- Division of Computing and Communication Foundations