paper-with-me

Papers

Privacy Amplification for the Gaussian Mechanism via Bounded Support

2024-03-07 · Shengyuan Hu, Saeed Mahloujifar, Virginia Smith, Kamalika Chaudhuri, Chuan Guo

Data-dependent privacy accounting frameworks such as per-instance differential privacy (pDP) and Fisher information loss (FIL) confer fine-grained privacy guarantees for individuals in a fixed training dataset. These guarantees can be desirable compared to vanilla DP in real world settings as they tightly upper-bound the privacy leakage for a $\textit{specific}$ individual in an $\textit{actual}$ dataset, rather than considering worst-case datasets. While these frameworks are beginning to gain popularity, to date, there is a lack of private mechanisms that can fully leverage advantages of data-dependent accounting. To bridge this gap, we propose simple modifications of the Gaussian mechanism with bounded support, showing that they amplify privacy guarantees under data-dependent accounting. Experiments on model training with DP-SGD show that using bounded support Gaussian mechanisms can provide a reduction of the pDP bound $\epsilon$ by as much as 30% without negative effects on model utility.

📄 PDF Abstract BibTeX arXiv:2403.05598

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Privacy Amplification by Mixing and Diffusion Mechanisms

2019-05-29 · NeurIPS 2019 12 · Borja Balle, Gilles Barthe, Marco Gaboardi, Joseph Geumlek

A fundamental result in differential privacy states that the privacy guarantees of a mechanism are preserved by any post-processing of its output. In this paper we investigate under what conditions stochastic post-proces…

Privacy Amplification Persists under Unlimited Synthetic Data Release

2026-02-03 · Clément Pierquin, Aurélien Bellet, Marc Tommasi, Matthieu Boussard arxiv

We study privacy amplification by synthetic data release, a phenomenon in which differential privacy guarantees are improved by releasing only synthetic data rather than the private generative model itself. Recent work b…

Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss

2022-05-27 · Jason M. Altschuler, Kunal Talwar

A central issue in machine learning is how to train models on sensitive user data. Industry has widely adopted a simple algorithm: Stochastic Gradient Descent with noise (a.k.a. Stochastic Gradient Langevin Dynamics). Ho…

Rényi Differential Privacy of the Sampled Gaussian Mechanism

2019-08-28 · Ilya Mironov, Kunal Talwar, Li Zhang

The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and the additive Gaussian noise---has been successfully used in a number of machine learning applications. The mechanism's unexpected power is derived f…

Privacy Amplification via Shuffled Check-Ins

2022-06-07 · Seng Pei Liew, Satoshi Hasegawa, Tsubasa Takahashi

We study a protocol for distributed computation called shuffled check-in, which achieves strong privacy guarantees without requiring any further trust assumptions beyond a trusted shuffler. Unlike most existing work, shu…

Federated Learning