Website Reputation System

Abstract

Because of the fast development of the web, sites have turned into the interloper’s principle target. As the quantity of web pages expands, the vindictive pages are likewise expanding and the assault is progressively turned out to be modern developing different ways to trick a client into visiting malicious websites extracting credential information. This paper presents a detailed account of ensemble based machine learning approach for URL classification. Models already existing either use outdated techniques or limited set of features in their attack detection model and thus leads to lower detection rate. But ensemble classifiers along with a selection of robust feature list for single and multi attack type detection outperform all the previous deployed techniques. Focus of the study is being able to come up with a system model that yields us better results with a higher accuracy rate.