Anonymizing multimedia documents

Abstract

Multimedia documents sharing and outsourcing have become part of the routine activity of many individuals and companies. Such data sharing puts at risk the privacy of individuals, whose identities need to be kept secret, when adversaries get the ability to associate the multimedia document’s content to possible trail of information left behind by the individual. 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 individuals. We provide a sanitizing MD∗-algorithm to enforce de-linkability along with a utility function to evaluate the utility of multimedia documents that is preserved after the sanitizing process. A set of experiments are elaborated to demonstrate the efficiency of our technique.