Abstract : Outsourcing social multimedia documents is a growing practice among several companies in a way to shift their business globally. It is a cost-effective process where those companies tend to gain more profits disregarding eventual privacy risks. In fact, several case studies have showed that adversaries are capable of identify-ing individuals, whose identities need to be kept private, using the content of their multimedia documents. In this paper, we propose de-linkability, a privacy-preserving constraint to bound the amount of information outsourced that can be used to re-identify the in-dividual. We also provide a sanitizing MD * -algorithm to enforce de-linkability and present a set of experiments to demonstrate its efficiency.