Calibrating noise to sensitivity in private data analysis-英文文献.pdf

Calibrating Noise to Sensitivity in Private Data Analysis 1 1 2 3⋆ Cynthia Dwork , Frank McSherry , Kobbi Nissim , and Adam Smith 1 Microsoft Research, Silicon Valley. {dwork,mcsherry}@ 2 Ben-Gurion University. kobbi@cs.bgu.ac.il 3 Weizmann Institute of Science. adam.smith@weizmann.ac.il Abstract. We continue a line of research initiated in [10, 11] on privacy- preserving statistical databases. Consider a trusted server that holds a database of sensitive information. Given a query function f mapping databases to reals, the so-called true answer is the result of applying f to the database. To protect privacy, the true answer is perturbed by the addition of random noise generated according to a carefully chosen distribution, and this response, the true answer plus noise, is returned to the user. Previous work focused on the case of noisy sums, in which f = P g (x ), where x denotes the ith row of the database and g maps data- i i i base rows to [0, 1]. We extend the study to general functions f , proving that privacy can be preserved by calibrating the standard deviation of the noise according to the sensitivity of the function f . Roughly speak- ing, this is the amount that any single argument to f can change its output. The new analysis shows that for several particular applications substantially less noise is needed than was previously understood to be the case. The first step is a very clean characterization of privacy in terms of in