Speaker: Sid Stamm, Indiana University and RavenWhite
Title: Combatting Click Fraud using Premium Clicks
Abstract:
We describe new techniques to combat the problem of click fraud in
pay-per-click (PPC) systems. Rather than adopting the common approach
of filtering out seemingly fraudulent clicks, we consider instead an
affirmative approach that only accepts legitimate clicks, namely
those validated through client authentication. Our system supports a
new advertising model in which ?premium? validated clicks assume
higher value than ordinary clicks of more uncertain authenticity.
Click validation in our system relies upon sites sharing evidence of
the legitimacy of users (distinguishing them from bots, scripts, or
fraudsters). As cross-site user tracking raises privacy concerns
among many users, we propose ways to make the process of
authentication anonymous. We also discuss deployment on mobile
devices as well as difficulties that may arise.