# Capacity Bounded Differential Privacy

arXiv: https://arxiv.org/abs/1907.02159 · HTML: https://mlsanity.com/paper/1907.02159/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2019.

## Built on by (most cited first, 5 of 5)

- [Generative Adversarial Networks: A Survey Towards Private and Secure Applications](https://mlsanity.com/paper/2106.03785/) (2021)
- [ULDP-FL: Federated Learning with Across Silo User-Level Differential Privacy](https://mlsanity.com/paper/2308.12210/) (2023)
- [Algorithms with More Granular Differential Privacy Guarantees](https://mlsanity.com/paper/2209.04053/) (2022)
- [Can Membership Inferencing be Refuted?](https://mlsanity.com/paper/2303.03648/) (2023)
- [Auditing Differential Privacy in High Dimensions with the Kernel Quantum R'enyi Divergence](https://mlsanity.com/paper/2205.13941/) (2022)

## Abstract (arXiv)

Differential privacy, a notion of algorithmic stability, is a gold standard for measuring the additional risk an algorithm's output poses to the privacy of a single record in the dataset. Differential privacy is defined as the distance between the output distribution of an algorithm on neighboring datasets that differ in one entry. In this work, we present a novel relaxation of differential privacy, capacity bounded differential privacy, where the adversary that distinguishes output distributions is assumed to be capacity-bounded -- i.e. bounded not in computational power, but in terms of the function class from which their attack algorithm is drawn. We model adversaries in terms of restricted f-divergences between probability distributions, and study properties of the definition and algorithms that satisfy them.