Oblivious Sampling Algorithms for Private Data Analysis [article]

Sajin Sasy, Olga Ohrimenko
2020 arXiv   pre-print
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
more » ... 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.
arXiv:2009.13689v1 fatcat:lw2tgo5yhnbmhekhuwxd5wrosy