Holistic Collaborative Privacy Framework for Users' Privacy in Social Recommender Service

Nowadays, it is crucial to preserve the privacy of end-users while utilizing a third-party recommender service within content distribution networks so as to maintain their satisfaction and trust in the offered services. The current business model for those recommender services is centered around the availability of users’ personal data at their side whereas consumers have to trust that the recommender service providers will not use their data in a malicious way. With the increasing number of cases for privacy breaches of personal information, different countries and corporations have issued privacy laws and regulations to define the best practices for the protection of personal information. The data protection directive 95/46/EC and the privacy principles established by the Organization for Economic Cooperation and Development (OECD) are examples of such regulation frameworks. In this paper, we assert that utilizing third-party recommender services to generate accurate referrals are feasible, while preserving the privacy of the users’ sensitive information which will be residing on a clear form only on his/her own device. As a result, each user who benefits from the third-party recommender service will have absolute control over what to release from his/her own preferences. To support this claim, we proposed a collaborative privacy middleware that executes a two stage concealment process within a distributed data collection protocol in order to attain this claim. Additionally, the proposed solution complies with one of the common privacy regulation frameworks for fair information practice in a natural and functional way which is OECD privacy principles. The approach presented in this paper is easily integrated into the current business model as it is implemented using a middleware that runs at the end-users side and utilizes the social nature of content distribution services to implement a topological data collection protocol. We depicted how our middleware can be integrated into a scenario related to preserving the privacy of the users’ data which is utilized by a third party recommendation service in order to generate accurate referrals for users of mobile jukebox services while maintaining their sensitive information at their own side. Our collaborative privacy framework induces a straightforward solution with accurate results which are beneficial to both users and service providers.