期刊名称：Proceedings on Privacy Enhancing Technologies
电子版ISSN：2299-0984
出版年度：2020
卷号：2020
期号：4
页码：5-23
DOI：10.2478/popets-2020-0060
语种：English
出版社：Sciendo
摘要：Differential privacy is a mathematical framework for privacy-preserving data analysis. Changing the hyperparameters of a differentially private algorithm allows one to trade off privacy and utility in a principled way. Quantifying this trade-off in advance is essential to decision-makers tasked with deciding how much privacy can be provided in a particular application while maintaining acceptable utility. Analytical utility guarantees offer a rigorous tool to reason about this tradeoff,but are generally only available for relatively simple problems. For more complex tasks,such as training neural networks under differential privacy,the utility achieved by a given algorithm can only be measured empirically. This paper presents a Bayesian optimization methodology for efficiently characterizing the privacy– utility trade-off of any differentially private algorithm using only empirical measurements of its utility. The versatility of our method is illustrated on a number of machine learning tasks involving multiple models,optimizers,and datasets.
