paper-with-me

홈 › Papers

Renyi Differential Privacy Mechanisms for Posterior Sampling

2017-12-01 · NeurIPS 2017 12 · Joseph Geumlek, Shuang Song, Kamalika Chaudhuri

With the newly proposed privacy definition of Rényi Differential Privacy (RDP) in (Mironov, 2017), we re-examine the inherent privacy of releasing a single sample from a posterior distribution. We exploit the impact of the prior distribution in mitigating the influence of individual data points. In particular, we focus on sampling from an exponential family and specific generalized linear models, such as logistic regression. We propose novel RDP mechanisms as well as offering a new RDP analysis for an existing method in order to add value to the RDP framework. Each method is capable of achieving arbitrary RDP privacy guarantees, and we offer experimental results of their efficacy.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Similar Papers 제목 키워드 기반

Geometric Renyi Differential Privacy: Ricci Curvature Characterized by Heat Diffusion Mechanisms

2026-04-22 · Xiaotian Chang, Yangdi Jiang, Cyrus Mostajeran, Qirui Hu arxiv

In this paper, we develop a novel privacy mechanism for Riemannian manifold-valued data. Our key contribution lies in uncovering unexpected connections among geometric analysis, heat diffusion models, and differential pr…

On the Renyi Differential Privacy of the Shuffle Model

2021-05-11 · Antonious M. Girgis, Deepesh Data, Suhas Diggavi, Ananda Theertha Suresh 외

The central question studied in this paper is Renyi Differential Privacy (RDP) guarantees for general discrete local mechanisms in the shuffle privacy model. In the shuffle model, each of the $n$ clients randomizes its r…

Rényi Differential Privacy Mechanisms for Posterior Sampling

2017-10-02 · Joseph Geumlek, Shuang Song, Kamalika Chaudhuri

Using a recently proposed privacy definition of R\'enyi Differential Privacy (RDP), we re-examine the inherent privacy of releasing a single sample from a posterior distribution. We exploit the impact of the prior distri…

regression

Differential Privacy of Gaussian Process Posterior Sampling

2026-06-16 · Tomasz Maciazek arxiv

We study the privacy of releasing posterior sample paths from a Gaussian process (GP) when the entire training set including covariates and responses is private. Unlike standard differential-privacy (DP) mechanisms that …

Bayesian Differential Privacy through Posterior Sampling

2013-06-05 · Christos Dimitrakakis, Blaine Nelson, and Zuhe Zhang, Aikaterini Mitrokotsa 외

Differential privacy formalises privacy-preserving mechanisms that provide access to a database. We pose the question of whether Bayesian inference itself can be used directly to provide private access to data, with no m…

Bayesian InferencePrivacy Preserving