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

Clément Pierquin, Aurélien Bellet, Marc Tommasi, Matthieu Boussard
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:40762-40794, 2024.

Abstract

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 framework does not provide the composition guarantees needed for a direct use in iterative machine learning algorithms. To mitigate these issues, we introduce a Rényi divergence-based variant of Pufferfish and show that it allows us to extend the applicability of the Pufferfish framework. We first generalize the Wasserstein mechanism to cover a wide range of noise distributions and introduce several ways to improve its utility. Finally, as an alternative to composition, we prove privacy amplification results for contractive noisy iterations and showcase the first use of Pufferfish in private convex optimization. A common ingredient underlying our results is the use and extension of shift reduction lemmas.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-pierquin24a, title = {Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration via Shift Reduction Lemmas}, author = {Pierquin, Cl\'{e}ment and Bellet, Aur\'{e}lien and Tommasi, Marc and Boussard, Matthieu}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {40762--40794}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/pierquin24a/pierquin24a.pdf}, url = {https://proceedings.mlr.press/v235/pierquin24a.html}, abstract = {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 framework does not provide the composition guarantees needed for a direct use in iterative machine learning algorithms. To mitigate these issues, we introduce a Rényi divergence-based variant of Pufferfish and show that it allows us to extend the applicability of the Pufferfish framework. We first generalize the Wasserstein mechanism to cover a wide range of noise distributions and introduce several ways to improve its utility. Finally, as an alternative to composition, we prove privacy amplification results for contractive noisy iterations and showcase the first use of Pufferfish in private convex optimization. A common ingredient underlying our results is the use and extension of shift reduction lemmas.} }
Endnote
%0 Conference Paper %T Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration via Shift Reduction Lemmas %A Clément Pierquin %A Aurélien Bellet %A Marc Tommasi %A Matthieu Boussard %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-pierquin24a %I PMLR %P 40762--40794 %U https://proceedings.mlr.press/v235/pierquin24a.html %V 235 %X 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 framework does not provide the composition guarantees needed for a direct use in iterative machine learning algorithms. To mitigate these issues, we introduce a Rényi divergence-based variant of Pufferfish and show that it allows us to extend the applicability of the Pufferfish framework. We first generalize the Wasserstein mechanism to cover a wide range of noise distributions and introduce several ways to improve its utility. Finally, as an alternative to composition, we prove privacy amplification results for contractive noisy iterations and showcase the first use of Pufferfish in private convex optimization. A common ingredient underlying our results is the use and extension of shift reduction lemmas.
APA
Pierquin, C., Bellet, A., Tommasi, M. & Boussard, M.. (2024). Rényi Pufferfish Privacy: General Additive Noise Mechanisms and Privacy Amplification by Iteration via Shift Reduction Lemmas. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:40762-40794 Available from https://proceedings.mlr.press/v235/pierquin24a.html.

Related Material