Privacy protection in personalized search

Abstract

Personalized search is a promising way to improve the accuracy of web search, and has been attracting much attention recently. However, effective personalized search requires collecting and aggregating user information, which often raise serious concerns of privacy infringement for many users. Indeed, these concerns have become one of the main barriers for deploying personalized search applications, and how to do privacy-preserving personalization is a great challenge. In this paper, we systematically examine the issue of privacy preservation in personalized search. We distinguish and define four levels of privacy protection, and analyze various software architectures for personalized search. We show that client-side personalization has advantages over the existing server-side personalized search services in preserving privacy, and envision possible future strategies to fully protect user privacy.