Proactive Detection of Phishing Web Sites

Abstract

We will present in this talk an approach for pro-active detection of phishing web sites. The main idea consists in learning from data the underlying language model used by phishing attackers to generate phishing URLs. We will show how approaches used in natural language processing (HMMs) and semantic distances can be used to learn and predict potential phishing web sites. We will review the most features that can be used for such purposes and show comparative results with alternative approaches.

Biography

Radu State is a senior researcher with the Interdisciplinary Center on Security and Trust in Luxembourg. He was a former professor at the University of Lorraine and a senior researcher at INRIA Nancy, Grand Est. Having authored more then 100 papers, his research interests cover network and system security and management. He holds a Ph.D and a HDR from University of Lorraine and a M.Sc from the Johns Hopkins University.