A novel mail filtering method against phishing

Abstract

We focus on phishing in the mail filtering research. So we define a sender reliance cost by the DNS inquiry and the contents analysis. In this paper, we propose the method to estimate these costs quantitatively. In this proposed method, the cost which characteristics settle Phishing is obtained from the actual proof experiment and we show the Phishing filter calculated from a result of the experiment. Furthermore, we report about the prototype which implemented that mail filter as an extension of MTA, and show the validity of the proposed method from these actual outputted data.