On Hit Inflation Techniques and Detection in Streams of Web Advertising Networks

Abstract

Click fraud is jeopardizing the industry of Internet advertising. Internet advertising is crucial for the thriving of the entire Internet, since it allows producers to advertise their products, and hence contributes to the well being of ecommerce. Moreover, advertising supports the intellectual value of the Internet by covering the running expenses of the content publishers' sites. Some publishers are dishonest, and use automation to generate traffic to defraud the advertisers. Similarly, some advertisers automate clicks on the advertisements of their competitors to deplete their competitors' advertising budgets. In this paper, we describe the advertising network model, and discuss the issue of fraud that is an integral problem in such setting. We propose using online algorithms on aggregate data to accurately and proactively detect automated traffic, preserve surfers' privacy, while not altering the industry model. We provide a complete classification of the hit inflation techniques; and devise stream analysis techniques that detect a variety of fraud attacks. We abstract detecting the fraud attacks of some classes as theoretical stream analysis problems that we bring to the data management research community as open problems. A framework is outlined for deploying the proposed detection algorithms on a generic architecture. We conclude by some successful preliminary findings of our attempt to detect fraud on a real network.