Bayesian Adversarial Privacy
math.ST, cs.CR, cs.LG, stat.ME, stat.TH
Submitted: 2026-03-04
Updated: 2026-09-08
License: http://creativecommons.org/licenses/by/4.0/
The gist: Theoretical and applied research into privacy encompasses an incredibly broad swathe of differing approaches, emphases and aims.
Terminology
Abstract
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.
Sources
- Bayesian Federated Learning: A Survey
- Inferential Privacy Guarantees for Differentially Private Mechanisms
Related papers
- Conformal Prediction for Dyadic Regression Under Complex Missingness
- Bentkus-type asymptotic e-values
- High-Dimensional Asymptotics of Differentially Private PCA
- KL Convergence Guarantees for Score diffusion models under minimal data assumptions
- Geometric bias in eigenspace perturbation under random heterogeneous noise
- On the Asymptotic Inadmissibility of Double Machine Learning Estimators Under Structure-Agnostic Models