# Differentially Private Database Release via Kernel Mean Embeddings

arXiv: https://arxiv.org/abs/1710.01641 · HTML: https://mlsanity.com/paper/1710.01641/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2017.

## Built on by (most cited first, 12 of 12)

- [ADePT: Auto-encoder based Differentially Private Text Transformation](https://mlsanity.com/paper/2102.01502/) (2021)
- [Nystr"om Kernel Mean Embeddings](https://mlsanity.com/paper/2201.13055/) (2022)
- [Hermite Polynomial Features for Private Data Generation](https://mlsanity.com/paper/2106.05042/) (2021)
- [Controlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learning](https://mlsanity.com/paper/2112.00423/) (2021)
- [Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling](https://mlsanity.com/paper/2311.13548/) (2023)
- [From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis](https://mlsanity.com/paper/2504.01395/) (2025)
- [Differentially Private Low-dimensional Synthetic Data from High-dimensional Datasets](https://mlsanity.com/paper/2305.17148/) (2023)
- [Coefficient-based Regularized Distribution Regression](https://mlsanity.com/paper/2208.12427/) (2022)
- [Differentially Private Synthetic Data with Private Density Estimation](https://mlsanity.com/paper/2405.04554/) (2024)
- [Differentially Private Synthetic Data Using KD-Trees](https://mlsanity.com/paper/2306.13211/) (2023)
- [RFFNet: Large-Scale Interpretable Kernel Methods via Random Fourier Features](https://mlsanity.com/paper/2211.06410/) (2022)
- [M2M: A general method to perform various data analysis tasks from a differentially private sketch](https://mlsanity.com/paper/2211.14062/) (2022)

## Abstract (arXiv)

We lay theoretical foundations for new database release mechanisms that allow third-parties to construct consistent estimators of population statistics, while ensuring that the privacy of each individual contributing to the database is protected. The proposed framework rests on two main ideas. First, releasing (an estimate of) the kernel mean embedding of the data generating random variable instead of the database itself still allows third-parties to construct consistent estimators of a wide class of population statistics. Second, the algorithm can satisfy the definition of differential privacy by basing the released kernel mean embedding on entirely synthetic data points, while controlling accuracy through the metric available in a Reproducing Kernel Hilbert Space. We describe two instantiations of the proposed framework, suitable under different scenarios, and prove theoretical results guaranteeing differential privacy of the resulting algorithms and the consistency of estimators constructed from their outputs.