A static approach to detect drive-by-download attacks on webpages

Today, Internet has become another life to most of us. Other than a basic communication network, Internet has developed to be an interconnected information source, enabling different forms of social interactions and marketing. Cyber criminals use computer as a weapon to enrich themselves by taking undue advantage of legitimate sites. A serious threat in Web browsing is that the attackers use drive-by-download exploits by embedding malicious codes into web pages. When user with vulnerable browser visits this page, browser gets compromised. Here a static method is discussed to extract useful information from Web page and analyses it for the presence of malicious content. Based on the features extracted from the HTML contents of a Web page, different classifiers are implemented and tested in MATLAB and their detection accuracies are compared. Classifying algorithms of WEKA are also used for the study and their performance is compared.