Winning the NIST Contest: A scalable and general approach to differentially private synthetic data. McKenna, R., Miklau, G., & Sheldon, D. arXiv:2108.04978 [cs], August, 2021. arXiv: 2108.04978![Winning the NIST Contest: A scalable and general approach to differentially private synthetic data [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex We propose a general approach for differentially private synthetic data generation, that consists of three steps: (1) select a collection of low-dimensional marginals, (2) measure those marginals with a noise addition mechanism, and (3) generate synthetic data that preserves the measured marginals well. Central to this approach is Private-PGM, a post-processing method that is used to estimate a high-dimensional data distribution from noisy measurements of its marginals. We present two mechanisms, NIST-MST and MST, that are instances of this general approach. NIST-MST was the winning mechanism in the 2018 NIST differential privacy synthetic data competition, and MST is a new mechanism that can work in more general settings, while still performing comparably to NIST-MST. We believe our general approach should be of broad interest, and can be adopted in future mechanisms for synthetic data generation.
@article{mckenna_winning_2021,
title = {Winning the {NIST} {Contest}: {A} scalable and general approach to differentially private synthetic data},
shorttitle = {Winning the {NIST} {Contest}},
url = {http://arxiv.org/abs/2108.04978},
abstract = {We propose a general approach for differentially private synthetic data generation, that consists of three steps: (1) select a collection of low-dimensional marginals, (2) measure those marginals with a noise addition mechanism, and (3) generate synthetic data that preserves the measured marginals well. Central to this approach is Private-PGM, a post-processing method that is used to estimate a high-dimensional data distribution from noisy measurements of its marginals. We present two mechanisms, NIST-MST and MST, that are instances of this general approach. NIST-MST was the winning mechanism in the 2018 NIST differential privacy synthetic data competition, and MST is a new mechanism that can work in more general settings, while still performing comparably to NIST-MST. We believe our general approach should be of broad interest, and can be adopted in future mechanisms for synthetic data generation.},
urldate = {2021-08-16},
journal = {arXiv:2108.04978 [cs]},
author = {McKenna, Ryan and Miklau, Gerome and Sheldon, Daniel},
month = aug,
year = {2021},
note = {arXiv: 2108.04978},
keywords = {cryptography, mentions sympy},
}
Downloads: 0
{"_id":"MH7MxZYHzdm7Mfuep","bibbaseid":"mckenna-miklau-sheldon-winningthenistcontestascalableandgeneralapproachtodifferentiallyprivatesyntheticdata-2021","author_short":["McKenna, R.","Miklau, G.","Sheldon, D."],"bibdata":{"bibtype":"article","type":"article","title":"Winning the NIST Contest: A scalable and general approach to differentially private synthetic data","shorttitle":"Winning the NIST Contest","url":"http://arxiv.org/abs/2108.04978","abstract":"We propose a general approach for differentially private synthetic data generation, that consists of three steps: (1) select a collection of low-dimensional marginals, (2) measure those marginals with a noise addition mechanism, and (3) generate synthetic data that preserves the measured marginals well. Central to this approach is Private-PGM, a post-processing method that is used to estimate a high-dimensional data distribution from noisy measurements of its marginals. We present two mechanisms, NIST-MST and MST, that are instances of this general approach. NIST-MST was the winning mechanism in the 2018 NIST differential privacy synthetic data competition, and MST is a new mechanism that can work in more general settings, while still performing comparably to NIST-MST. We believe our general approach should be of broad interest, and can be adopted in future mechanisms for synthetic data generation.","urldate":"2021-08-16","journal":"arXiv:2108.04978 [cs]","author":[{"propositions":[],"lastnames":["McKenna"],"firstnames":["Ryan"],"suffixes":[]},{"propositions":[],"lastnames":["Miklau"],"firstnames":["Gerome"],"suffixes":[]},{"propositions":[],"lastnames":["Sheldon"],"firstnames":["Daniel"],"suffixes":[]}],"month":"August","year":"2021","note":"arXiv: 2108.04978","keywords":"cryptography, mentions sympy","bibtex":"@article{mckenna_winning_2021,\n\ttitle = {Winning the {NIST} {Contest}: {A} scalable and general approach to differentially private synthetic data},\n\tshorttitle = {Winning the {NIST} {Contest}},\n\turl = {http://arxiv.org/abs/2108.04978},\n\tabstract = {We propose a general approach for differentially private synthetic data generation, that consists of three steps: (1) select a collection of low-dimensional marginals, (2) measure those marginals with a noise addition mechanism, and (3) generate synthetic data that preserves the measured marginals well. Central to this approach is Private-PGM, a post-processing method that is used to estimate a high-dimensional data distribution from noisy measurements of its marginals. We present two mechanisms, NIST-MST and MST, that are instances of this general approach. NIST-MST was the winning mechanism in the 2018 NIST differential privacy synthetic data competition, and MST is a new mechanism that can work in more general settings, while still performing comparably to NIST-MST. We believe our general approach should be of broad interest, and can be adopted in future mechanisms for synthetic data generation.},\n\turldate = {2021-08-16},\n\tjournal = {arXiv:2108.04978 [cs]},\n\tauthor = {McKenna, Ryan and Miklau, Gerome and Sheldon, Daniel},\n\tmonth = aug,\n\tyear = {2021},\n\tnote = {arXiv: 2108.04978},\n\tkeywords = {cryptography, mentions sympy},\n}\n\n\n\n\n\n\n\n\n\n\n\n","author_short":["McKenna, R.","Miklau, G.","Sheldon, D."],"key":"mckenna_winning_2021","id":"mckenna_winning_2021","bibbaseid":"mckenna-miklau-sheldon-winningthenistcontestascalableandgeneralapproachtodifferentiallyprivatesyntheticdata-2021","role":"author","urls":{"Paper":"http://arxiv.org/abs/2108.04978"},"keyword":["cryptography","mentions sympy"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero-group/nicoguaro/525293","dataSources":["YtBDXPDiQEyhyEDZC","fhHfrQgj3AaGp7e9E","qzbMjEJf5d9Lk78vE","45tA9RFoXA9XeH4MM","MeSgs2KDKZo3bEbxH","nSXCrcahhCNfzvXEY","ecatNAsyr4f2iQyGq","tpWeaaCgFjPTYCjg3"],"keywords":["cryptography","mentions sympy"],"search_terms":["winning","nist","contest","scalable","general","approach","differentially","private","synthetic","data","mckenna","miklau","sheldon"],"title":"Winning the NIST Contest: A scalable and general approach to differentially private synthetic data","year":2021}