Differentially Private Empirical Cumulative Distribution Functions

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Barczewski, Antoine, Mawass, Amal, Ramon, Jan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915144767897600
author Barczewski, Antoine
Mawass, Amal
Ramon, Jan
author_facet Barczewski, Antoine
Mawass, Amal
Ramon, Jan
contents In order to both learn and protect sensitive training data, there has been a growing interest in privacy preserving machine learning methods. Differential privacy has emerged as an important measure of privacy. We are interested in the federated setting where a group of parties each have one or more training instances and want to learn collaboratively without revealing their data. In this paper, we propose strategies to compute differentially private empirical distribution functions. While revealing complete functions is more expensive from the point of view of privacy budget, it may also provide richer and more valuable information to the learner. We prove privacy guarantees and discuss the computational cost, both for a generic strategy fitting any security model and a special-purpose strategy based on secret sharing. We survey a number of applications and present experiments.
format Preprint
id arxiv_https___arxiv_org_abs_2502_06651
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Differentially Private Empirical Cumulative Distribution Functions
Barczewski, Antoine
Mawass, Amal
Ramon, Jan
Cryptography and Security
In order to both learn and protect sensitive training data, there has been a growing interest in privacy preserving machine learning methods. Differential privacy has emerged as an important measure of privacy. We are interested in the federated setting where a group of parties each have one or more training instances and want to learn collaboratively without revealing their data. In this paper, we propose strategies to compute differentially private empirical distribution functions. While revealing complete functions is more expensive from the point of view of privacy budget, it may also provide richer and more valuable information to the learner. We prove privacy guarantees and discuss the computational cost, both for a generic strategy fitting any security model and a special-purpose strategy based on secret sharing. We survey a number of applications and present experiments.
title Differentially Private Empirical Cumulative Distribution Functions
topic Cryptography and Security
url https://arxiv.org/abs/2502.06651