Personalized Privacy Amplification via Importance Sampling

We examine the privacy-enhancing properties of importance sampling. In importance sampling, selection probabilities are heterogeneous and each selected data point is weighted by the reciprocal of its selection probability. Due to the heterogeneity of importance sampling, we express our results withi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-02
Hauptverfasser: Fay, Dominik, Mair, Sebastian, Sjölund, Jens
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Fay, Dominik
Mair, Sebastian
Sjölund, Jens
description We examine the privacy-enhancing properties of importance sampling. In importance sampling, selection probabilities are heterogeneous and each selected data point is weighted by the reciprocal of its selection probability. Due to the heterogeneity of importance sampling, we express our results within the framework of personalized differential privacy. We first consider the general case where an arbitrary personalized differentially private mechanism is subsampled with an arbitrary importance sampling distribution and show that the resulting mechanism also satisfies personalized differential privacy. This constitutes an extension of the established privacy amplification by subsampling result to importance sampling. Then, for any fixed mechanism, we derive the sampling distribution that achieves the optimal sampling rate subject to a worst-case privacy constraint. Empirically, we evaluate the privacy, efficiency, and accuracy of importance sampling on the example of k-means clustering.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2840415923</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2840415923</sourcerecordid><originalsourceid>FETCH-proquest_journals_28404159233</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwCkgtKs7PS8zJrEpNUQgoyixLTK5UcMwtyMlMy0xOLMnMz1Moy0xU8MwtyC8qScxLTlUITgTJ5qXzMLCmJeYUp_JCaW4GZTfXEGcP3YKi_MLS1OKS-Kz80iKg0cXxRhYmBiaGppZAhxCnCgD-JTdG</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2840415923</pqid></control><display><type>article</type><title>Personalized Privacy Amplification via Importance Sampling</title><source>Freely Accessible Journals</source><creator>Fay, Dominik ; Mair, Sebastian ; Sjölund, Jens</creator><creatorcontrib>Fay, Dominik ; Mair, Sebastian ; Sjölund, Jens</creatorcontrib><description>We examine the privacy-enhancing properties of importance sampling. In importance sampling, selection probabilities are heterogeneous and each selected data point is weighted by the reciprocal of its selection probability. Due to the heterogeneity of importance sampling, we express our results within the framework of personalized differential privacy. We first consider the general case where an arbitrary personalized differentially private mechanism is subsampled with an arbitrary importance sampling distribution and show that the resulting mechanism also satisfies personalized differential privacy. This constitutes an extension of the established privacy amplification by subsampling result to importance sampling. Then, for any fixed mechanism, we derive the sampling distribution that achieves the optimal sampling rate subject to a worst-case privacy constraint. Empirically, we evaluate the privacy, efficiency, and accuracy of importance sampling on the example of k-means clustering.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Amplification ; Cluster analysis ; Clustering ; Data points ; Importance sampling ; Privacy ; Vector quantization</subject><ispartof>arXiv.org, 2024-02</ispartof><rights>2024. This work is published under http://creativecommons.org/licenses/by-sa/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>781,785</link.rule.ids></links><search><creatorcontrib>Fay, Dominik</creatorcontrib><creatorcontrib>Mair, Sebastian</creatorcontrib><creatorcontrib>Sjölund, Jens</creatorcontrib><title>Personalized Privacy Amplification via Importance Sampling</title><title>arXiv.org</title><description>We examine the privacy-enhancing properties of importance sampling. In importance sampling, selection probabilities are heterogeneous and each selected data point is weighted by the reciprocal of its selection probability. Due to the heterogeneity of importance sampling, we express our results within the framework of personalized differential privacy. We first consider the general case where an arbitrary personalized differentially private mechanism is subsampled with an arbitrary importance sampling distribution and show that the resulting mechanism also satisfies personalized differential privacy. This constitutes an extension of the established privacy amplification by subsampling result to importance sampling. Then, for any fixed mechanism, we derive the sampling distribution that achieves the optimal sampling rate subject to a worst-case privacy constraint. Empirically, we evaluate the privacy, efficiency, and accuracy of importance sampling on the example of k-means clustering.</description><subject>Amplification</subject><subject>Cluster analysis</subject><subject>Clustering</subject><subject>Data points</subject><subject>Importance sampling</subject><subject>Privacy</subject><subject>Vector quantization</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwCkgtKs7PS8zJrEpNUQgoyixLTK5UcMwtyMlMy0xOLMnMz1Moy0xU8MwtyC8qScxLTlUITgTJ5qXzMLCmJeYUp_JCaW4GZTfXEGcP3YKi_MLS1OKS-Kz80iKg0cXxRhYmBiaGppZAhxCnCgD-JTdG</recordid><startdate>20240215</startdate><enddate>20240215</enddate><creator>Fay, Dominik</creator><creator>Mair, Sebastian</creator><creator>Sjölund, Jens</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20240215</creationdate><title>Personalized Privacy Amplification via Importance Sampling</title><author>Fay, Dominik ; Mair, Sebastian ; Sjölund, Jens</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28404159233</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Amplification</topic><topic>Cluster analysis</topic><topic>Clustering</topic><topic>Data points</topic><topic>Importance sampling</topic><topic>Privacy</topic><topic>Vector quantization</topic><toplevel>online_resources</toplevel><creatorcontrib>Fay, Dominik</creatorcontrib><creatorcontrib>Mair, Sebastian</creatorcontrib><creatorcontrib>Sjölund, Jens</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Fay, Dominik</au><au>Mair, Sebastian</au><au>Sjölund, Jens</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Personalized Privacy Amplification via Importance Sampling</atitle><jtitle>arXiv.org</jtitle><date>2024-02-15</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>We examine the privacy-enhancing properties of importance sampling. In importance sampling, selection probabilities are heterogeneous and each selected data point is weighted by the reciprocal of its selection probability. Due to the heterogeneity of importance sampling, we express our results within the framework of personalized differential privacy. We first consider the general case where an arbitrary personalized differentially private mechanism is subsampled with an arbitrary importance sampling distribution and show that the resulting mechanism also satisfies personalized differential privacy. This constitutes an extension of the established privacy amplification by subsampling result to importance sampling. Then, for any fixed mechanism, we derive the sampling distribution that achieves the optimal sampling rate subject to a worst-case privacy constraint. Empirically, we evaluate the privacy, efficiency, and accuracy of importance sampling on the example of k-means clustering.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2024-02
issn 2331-8422
language eng
recordid cdi_proquest_journals_2840415923
source Freely Accessible Journals
subjects Amplification
Cluster analysis
Clustering
Data points
Importance sampling
Privacy
Vector quantization
title Personalized Privacy Amplification via Importance Sampling
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-11T16%3A51%3A18IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Personalized%20Privacy%20Amplification%20via%20Importance%20Sampling&rft.jtitle=arXiv.org&rft.au=Fay,%20Dominik&rft.date=2024-02-15&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2840415923%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2840415923&rft_id=info:pmid/&rfr_iscdi=true