Communication Dans Un Congrès Année : 2025

Privacy Amplification Through Synthetic Data: Insights from Linear Regression

Résumé

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.

Fichier principal
Vignette du fichier
2506.05101v1.pdf (835.95 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05237878 , version 1 (03-09-2025)

Licence

Identifiants

Citer

Clément Pierquin, Aurélien Bellet, Marc Tommasi, Matthieu Boussard. Privacy Amplification Through Synthetic Data: Insights from Linear Regression. ICML 2025 - 42nd International Conference on Machine Learning, 2025, Vancouver, Canada. ⟨10.48550/arXiv.2506.05101⟩. ⟨hal-05237878⟩
394 Consultations
422 Téléchargements

Altmetric

Partager

  • More