Privacy Preserving Personalized Data in Face Book by using Rank Based Algorithm

Personalized recommendation is important to find relevant information to customers. It often relies on a large collection of user data, in particular users’ online activity on social media, to mine user preference. However, releasing such user activity data makes users vulnerable to inference attacks, as private data will often be inferred from the users’ activity data. In this, we proposed PrivRank, a customizable and continuous privacy-preserving social media data publishing framework protecting users against inference attacks while enabling personalized ranking-based recommendations. Its key idea is to continuously obfuscate user activity data such that the privacy leakage of user-specified private data is reduced under a given data distortion budget, which bounds the ranking loss incurred from the info obfuscation method in order to preserve the utility of the data for enabling recommendations In this , we plan to extend our framework by considering the data types with continuous values rather than discredited values, and explore further data utility beyond personalized recommendation.