Persuasive Privacy

Joshua J Bon, James Bailie, Judith Rousseau, Christian P Robert
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:9015-9038, 2026.

Abstract

We propose a novel framework for measuring privacy from a Bayesian game-theoretic perspective. This framework enables the creation of new, purpose-driven privacy definitions that are rigorously justified, while also allowing for the assessment of existing privacy guarantees through game theory. We show that pure and probabilistic differential privacy are special cases of our framework, and provide new interpretations of the post-processing inequality in these settings. Further, we demonstrate that privacy guarantees can be established for deterministic algorithms, which are overlooked by current privacy standards.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-bon26a, title = {Persuasive Privacy}, author = {Bon, Joshua J and Bailie, James and Rousseau, Judith and Robert, Christian P}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {9015--9038}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/bon26a/bon26a.pdf}, url = {https://proceedings.mlr.press/v306/bon26a.html}, abstract = {We propose a novel framework for measuring privacy from a Bayesian game-theoretic perspective. This framework enables the creation of new, purpose-driven privacy definitions that are rigorously justified, while also allowing for the assessment of existing privacy guarantees through game theory. We show that pure and probabilistic differential privacy are special cases of our framework, and provide new interpretations of the post-processing inequality in these settings. Further, we demonstrate that privacy guarantees can be established for deterministic algorithms, which are overlooked by current privacy standards.} }
Endnote
%0 Conference Paper %T Persuasive Privacy %A Joshua J Bon %A James Bailie %A Judith Rousseau %A Christian P Robert %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-bon26a %I PMLR %P 9015--9038 %U https://proceedings.mlr.press/v306/bon26a.html %V 306 %X We propose a novel framework for measuring privacy from a Bayesian game-theoretic perspective. This framework enables the creation of new, purpose-driven privacy definitions that are rigorously justified, while also allowing for the assessment of existing privacy guarantees through game theory. We show that pure and probabilistic differential privacy are special cases of our framework, and provide new interpretations of the post-processing inequality in these settings. Further, we demonstrate that privacy guarantees can be established for deterministic algorithms, which are overlooked by current privacy standards.
APA
Bon, J.J., Bailie, J., Rousseau, J. & Robert, C.P.. (2026). Persuasive Privacy. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:9015-9038 Available from https://proceedings.mlr.press/v306/bon26a.html.

Related Material