Anomaly Based Web Phishing Page Detection

The idea is to examine the anomalies in Web pages, in particular, the discrepancy between a Web site's identity and its structural features and HTTP transactions, which demands neither user expertise nor prior knowledge of the Web site.

Abstract

Many anti-phishing schemes have recently been proposed in literature. Despite all those efforts, the threat of phishing attacks is not mitigated. One of the main reasons is that phishing attackers have the adaptability to change their tactics with little cost. In this paper, we propose a novel approach, which is independent of any specific phishing implementation. Our idea is to examine the anomalies in Web pages, in particular, the discrepancy between a Web site's identity and its structural features and HTTP transactions. It demands neither user expertise nor prior knowledge of the Web site. The evasion of our phishing detection entails high cost to the adversary. As shown by the experiments, our phishing detector functions with low miss rate and low false-positive rate