Clément Pierquin — accepted AI-conference papers

2025

Privacy Amplification Through Synthetic Data: Insights from Linear Regression

Clément Pierquin, Aurélien Bellet, Marc Tommasi, Matthieu Boussard

ICML 2025poster

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 l…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration via Shift Reduction Lemmas

Clément Pierquin, Aurélien Bellet, Marc Tommasi, Matthieu Boussard

ICML 2024poster

Pufferfish privacy is a flexible generalization of differential privacy that allows to model arbitrary secrets and adversary's prior knowledge about the data. Unfortunately, designing general and tractable Pufferfish mechanisms that do not compromise utility is challenging. Furthermore, this framewo…

Cited by 3 Source ↗PDF ↗Scholar ↗