Privacy Amplification Through Synthetic Data: Insights from Linear Regression

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pierquin, Clément, Bellet, Aurélien, Tommasi, Marc, Boussard, Matthieu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909639498530816
author Pierquin, Clément
Bellet, Aurélien
Tommasi, Marc
Boussard, Matthieu
author_facet Pierquin, Clément
Bellet, Aurélien
Tommasi, Marc
Boussard, Matthieu
contents Synthetic data inherits the differential privacy guarantees of the model used to generate it. Additionally, synthetic data may benefit from privacy amplification when the generative model is kept hidden. While empirical studies suggest this phenomenon, a rigorous theoretical understanding is still lacking. In this paper, we investigate this question through the well-understood framework of linear regression. First, we establish negative results showing that if an adversary controls the seed of the generative model, a single synthetic data point can leak as much information as releasing the model itself. Conversely, we show that when synthetic data is generated from random inputs, releasing a limited number of synthetic data points amplifies privacy beyond the model's inherent guarantees. We believe our findings in linear regression can serve as a foundation for deriving more general bounds in the future.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05101
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Privacy Amplification Through Synthetic Data: Insights from Linear Regression
Pierquin, Clément
Bellet, Aurélien
Tommasi, Marc
Boussard, Matthieu
Machine Learning
Cryptography and Security
Synthetic data inherits the differential privacy guarantees of the model used to generate it. Additionally, synthetic data may benefit from privacy amplification when the generative model is kept hidden. While empirical studies suggest this phenomenon, a rigorous theoretical understanding is still lacking. In this paper, we investigate this question through the well-understood framework of linear regression. First, we establish negative results showing that if an adversary controls the seed of the generative model, a single synthetic data point can leak as much information as releasing the model itself. Conversely, we show that when synthetic data is generated from random inputs, releasing a limited number of synthetic data points amplifies privacy beyond the model's inherent guarantees. We believe our findings in linear regression can serve as a foundation for deriving more general bounds in the future.
title Privacy Amplification Through Synthetic Data: Insights from Linear Regression
topic Machine Learning
Cryptography and Security
url https://arxiv.org/abs/2506.05101