Scalable Detection and Isolation of Phishing

摘要

This paper presents a proposal for scalable detection and isolation of phishing. The main ideas are to move the protection from end users towards the network provider and to employ the novel bad neighbourhood concept, in order to detect and isolate both phishing e-mail senders and phishing web servers. In addition, we propose to develop a self-management architecture that enables ISPs to protect their users against phishing attacks, and explain how this architecture could be evaluated. This proposal is the result of half a year of research work at the University of Twente (UT), and it is aimed at a Ph.D. thesis in 2012.