Hypothesis Testing Interpretations and Renyi Differential Privacy

By Borja Balle, Gilles Barthe, Marco Gaboardi, Justin Hsu, Tetsuya Sato. 2019

155 citations recorded by the source corpus.

Differential privacy is a de facto standard in data privacy, with applications in the public and private sectors. A way to explain differential privacy, which is particularly appealing to statistician and social scientists is by means of its statistical hypothesis testing interpretation. Informally, one cannot effectively test whether a specific individual has contributed her data by observing the output of a private mechanism---any test cannot have both high significance and high power. In this paper, we identify some conditions under which a privacy definition given in terms of a statistical divergence satisfies a similar interpretation. These conditions are useful to analyze the distinguishability power of divergences and we use them to study the hypothesis testing interpretation of some relaxations of differential privacy based on Renyi divergence. This analysis also results in an improved conversion rule between these definitions and differential privacy.

Subfields: Artificial Intelligence, Sociology and Political Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Sociology and Political Science

Citations in the corpus

The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation (2021, methodology): “For more information on the shuffled model of DP, we refer the reader to Ghazi et al. (2020b; 2021; 2020c;a); Ishai et al. (2006); Balle et al. (2019; 2020); Balcer & Cheu (2020); Balcer et al. (2021); Girgis et al. (2020).”
Robust Aggregation for Federated Learning (2019, methodology): “2 Related Work Federated Learning was introduced in [66] as a distributed optimization approach to handle on-device machine learning, with secure multi-party averaging algorithms given in [9, 17].”
TAN without a burn: Scaling Laws of DP-SGD (2022, methodology): “In this work, we use the accountant due to (Balle et al., 2020), whose output is referred to as ε, which is slightly smaller than εRDP.”
Differentially Private Federated Learning: An Information-Theoretic Perspective (2021, background): “For instance, each iteration of the projected noisy stochastic gradient descent with Gaussian noise (see e.g., [4, 5, 7, 8, 11, 30]) can be viewed as a Gaussian kernel whose input (and output) are values from a compact set.”