Collaborative privacy framework for minimizing privacy risks in an IPTV social recommender service

Abstract

In our connected world, recommender systems have become widely known for their ability to provide expert and personalized referrals to end-users in different domains. The rapid growth of social networks has given a rise to a new kind of systems, which have been termed "social recommender service". In this context, a software as a service recommender system can be utilized to extract a set of suitable referrals for certain users based on the data collected from the personal profiles of other end-users within a social structure. However, preserving end-users privacy in social recommender services is a very challenging problem that might prevent privacy concerned users from releasing their own profiles' data or to be forced to release an erroneous data. Thus, both cases can detain the accuracy of extracted referrals. So in order to gain accurate referrals, the social recommender service should have the ability to preserve the privacy of end-users registered in their system. In this paper, we present a middleware that runs on the end-users' side in order to conceal their profiles data when being released for the recommendation purposes. The computation of recommendation proceeds over this concealed data. The proposed middleware is equipped with a distributed data collection protocol along with two stage concealment process to give the end-users complete control over the privacy of their profiles. We will present an IPTV network scenario along with the proposed middleware. A number of different experiments were performed on real data which was concealed using our two stage concealment process to evaluate the achieved privacy and accuracy of the extracted referrals. As supported by the experiments, the proposed framework maintains the recommendations accuracy with a reasonable privacy level.