A Novel Approach for Detection of Malicious Websites using Machine Learning Techniques

Abstract

When an unsuspecting victim visits a malicious website, it infects her machine to steal valuable information, redirects her to malicious targets, or compromises her system to launch future attacks. While current approaches have. There are still open issues in effectively and efficiently addressing: filtering of web pages from the wild, coverage of a wide range of malicious characteristics to capture the big picture, continuous evolution of web page features, systematic combination of features, semantic implications of feature values on characterizing web pages, ease and cost of flexibility and scalability of analysis and detection technology. In this position paper, we highlight our ongoing efforts towards effective and efficient analysis and detection of malicious websites, with a particular emphasis on broader feature space and attack-payloads, technique flexibility with changes in malicious characteristics and web pages, and, most importantly, technique usability in defending users against malicious websites.