# Privacy Amplification for the Gaussian Mechanism via Bounded Support

arXiv: https://arxiv.org/abs/2403.05598 · HTML: https://mlsanity.com/paper/2403.05598/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 35 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Builds on (most cited first, 20 of 20)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Differential Privacy Has Disparate Impact on Model Accuracy](https://mlsanity.com/paper/1905.12101/) (2019)
- [BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers](https://mlsanity.com/paper/2208.06366/) (2022)
- [Unlocking High-Accuracy Differentially Private Image Classification through Scale](https://mlsanity.com/paper/2204.13650/) (2022)
- [R'enyi Differential Privacy of the Sampled Gaussian Mechanism](https://mlsanity.com/paper/1908.10530/) (2019)
- [The Discrete Gaussian for Differential Privacy](https://mlsanity.com/paper/2004.00010/) (2020)
- [The Skellam Mechanism for Differentially Private Federated Learning](https://mlsanity.com/paper/2110.04995/) (2021)
- [Individual Privacy Accounting via a Renyi Filter](https://mlsanity.com/paper/2008.11193/) (2020)
- [Bounding Training Data Reconstruction in Private (Deep) Learning](https://mlsanity.com/paper/2201.12383/) (2022)
- [Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees](https://mlsanity.com/paper/2002.10940/) (2020)
- [Measuring Data Leakage in Machine-Learning Models with Fisher Information](https://mlsanity.com/paper/2102.11673/) (2021)
- [Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation](https://mlsanity.com/paper/2304.01541/) (2023)
- [Individual Privacy Accounting with Gaussian Differential Privacy](https://mlsanity.com/paper/2209.15596/) (2022)
- [A bounded-noise mechanism for differential privacy](https://mlsanity.com/paper/2012.03817/) (2020)
- [The Bounded Laplace Mechanism in Differential Privacy](https://mlsanity.com/paper/1808.10410/) (2018)
- [Privately Publishable Per-instance Privacy](https://mlsanity.com/paper/2111.02281/) (2021)
- [A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization](https://mlsanity.com/paper/2212.04486/) (2022)
- [Individualized PATE: Differentially Private Machine Learning with Individual Privacy Guarantees](https://mlsanity.com/paper/2202.10517/) (2022)

## Built on by (most cited first, 2 of 2)

- [Adaptive Data Analysis for Growing Data](https://mlsanity.com/paper/2405.13375/) (2024)
- [The Geometry of Randomized Smoothing on Feasible Sets](https://mlsanity.com/paper/2609.39497/) (2026)

## Abstract (arXiv)

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 textitspecific individual in an textitactual 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 ε by as much as 30% without negative effects on model utility.