# Bayesian Adversarial Privacy

arXiv: https://arxiv.org/abs/2603.04199 · HTML: https://mlsanity.com/paper/2603.04199/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 49 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 15 of 15)

- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Federated Learning with Differential Privacy: Algorithms and Performance Analysis](https://mlsanity.com/paper/1911.00222/) (2019)
- [A General Framework for Updating Belief Distributions](https://mlsanity.com/paper/1306.6430/) (2013)
- [Modern Bayesian Experimental Design](https://mlsanity.com/paper/2302.14545/) (2023)
- [Safe Testing](https://mlsanity.com/paper/1906.07801/) (2019)
- [Hypothesis Testing Interpretations and Renyi Differential Privacy](https://mlsanity.com/paper/1905.09982/) (2019)
- [Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent](https://mlsanity.com/paper/2102.05855/) (2021)
- [Robust Generalised Bayesian Inference for Intractable Likelihoods](https://mlsanity.com/paper/2104.07359/) (2021)
- [SoK: Differential Privacies](https://mlsanity.com/paper/1906.01337/) (2019)
- [Bayesian Federated Learning: A Survey](https://mlsanity.com/paper/2304.13267/) (2023)
- [The Impact of the U.S. Census Disclosure Avoidance System on Redistricting and Voting Rights Analysis](https://mlsanity.com/paper/2105.14197/) (2021)
- [Inferential Privacy Guarantees for Differentially Private Mechanisms](https://mlsanity.com/paper/1603.01508/) (2016)
- [Statistical Data Privacy: A Song of Privacy and Utility](https://mlsanity.com/paper/2205.03336/) (2022)
- [Bayesian Estimation of Attribute and Identification Disclosure Risks in Synthetic Data](https://mlsanity.com/paper/1804.02784/) (2018)
- [Persuasive Privacy](https://mlsanity.com/paper/2601.22945/) (2026)

## Abstract (arXiv)

Theoretical and applied research into privacy encompasses an incredibly broad swathe of differing approaches, emphases and aims. This work introduces a novel quantitative notion of privacy that is both contextual and specific. Building on and extending ideas from statistical disclosure control and differential privacy, our aim is to model the implications of a disclosure decision in an adversarial setting. Our definition relies on concepts inherent to standard Bayesian decision theory, while departing from them in several important respects. In particular, (i) inference about the data itself becomes meaningful and (ii) the party controlling the release of sensitive information should make disclosure decisions from the prior viewpoint, rather than conditional on the data, which is a feature shared with Bayesian design. Illuminating toy examples are exploited towards highlighting the specificities of the method.