Privacy-Utility Trade-Off

Abstract

In this paper, we investigate the privacy-utility trade-off (PUT) problem, which considers the minimal privacy loss at a fixed expense of utility. Several different kinds of privacy in the PUT problem are studied, including differential privacy, approximate differential privacy, maximal information, maximal leakage, Renyi differential privacy, Sibson mutual information and mutual information. The average Hamming distance is used to measure the distortion caused by the privacy mechanism. We consider two scenarios: global privacy and local privacy. In the framework of global privacy framework, the privacy-distortion function is upper-bounded by the privacy loss of a special mechanism, and lower-bounded by the optimal privacy loss with any possible prior input distribution. In the framework of local privacy, we generalize a coloring method for the PUT problem.