# Oblivious Sampling Algorithms for Private Data Analysis

arXiv: https://arxiv.org/abs/2009.13689 · HTML: https://mlsanity.com/paper/2009.13689/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2020.

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

- [A Survey of Secure Computation Using Trusted Execution Environments](https://mlsanity.com/paper/2302.12150/) (2023)
- [Local Model Reconstruction Attacks in Federated Learning and their Uses](https://mlsanity.com/paper/2210.16205/) (2022)

## Abstract (arXiv)

We study secure and privacy-preserving data analysis based on queries executed on samples from a dataset. Trusted execution environments (TEEs) can be used to protect the content of the data during query computation, while supporting differential-private (DP) queries in TEEs provides record privacy when query output is revealed. Support for sample-based queries is attractive due to privacy amplification since not all dataset is used to answer a query but only a small subset. However, extracting data samples with TEEs while proving strong DP guarantees is not trivial as secrecy of sample indices has to be preserved. To this end, we design efficient secure variants of common sampling algorithms. Experimentally we show that accuracy of models trained with shuffling and sampling is the same for differentially private models for MNIST and CIFAR-10, while sampling provides stronger privacy guarantees than shuffling.