Private Protocols for U-Statistics in the Local Model and Beyond - Archive ouverte HAL Access content directly
Conference Papers Year :

Private Protocols for U-Statistics in the Local Model and Beyond

(1) , (2) , (3) , (4)
1
2
3
4

Abstract

In this paper, we study the problem of computing $U$-statistics of degree $2$, i.e., quantities that come in the form of averages over pairs of data points, in the local model of differential privacy (LDP). The class of $U$-statistics covers many statistical estimates of interest, including Gini mean difference, Kendall's tau coefficient and Area under the ROC Curve (AUC), as well as empirical risk measures for machine learning problems such as ranking, clustering and metric learning. We first introduce an LDP protocol based on quantizing the data into bins and applying randomized response, which guarantees an $\epsilon$-LDP estimate with a Mean Squared Error (MSE) of $O(1/\sqrt{n}\epsilon)$ under regularity assumptions on the $U$-statistic or the data distribution. We then propose a specialized protocol for AUC based on a novel use of hierarchical histograms that achieves MSE of $O(\alpha^3/n\epsilon^2)$ for arbitrary data distribution. We also show that 2-party secure computation allows to design a protocol with MSE of $O(1/n\epsilon^2)$, without any assumption on the kernel function or data distribution and with total communication linear in the number of users $n$. Finally, we evaluate the performance of our protocols through experiments on synthetic and real datasets.
Fichier principal
Vignette du fichier
aistats20_privacy.pdf (534.98 Ko) Télécharger le fichier
Vignette du fichier
aistats20_privacy_supp.pdf (568.23 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02310236 , version 1 (10-10-2019)
hal-02310236 , version 2 (04-05-2020)

Identifiers

Cite

James Bell, Aurélien Bellet, Adrià Gascón, Tejas Kulkarni. Private Protocols for U-Statistics in the Local Model and Beyond. AISTATS 2020 - 23rd International Conference on Artificial Intelligence and Statistics, Aug 2020, Palermo, Italy. ⟨hal-02310236v2⟩
125 View
103 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More