Loading…

A Unified View of Differentially Private Deep Generative Modeling

The availability of rich and vast data sources has greatly advanced machine learning applications in various domains. However, data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing. Overcoming these obstacles in compliance with privacy co...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-09
Main Authors: Chen, Dingfan, Kerkouche, Raouf, Fritz, Mario
Format: Article
Language:English
Subjects:
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Chen, Dingfan
Kerkouche, Raouf
Fritz, Mario
description The availability of rich and vast data sources has greatly advanced machine learning applications in various domains. However, data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing. Overcoming these obstacles in compliance with privacy considerations is key for technological progress in many real-world application scenarios that involve privacy sensitive data. Differentially private (DP) data publishing provides a compelling solution, where only a sanitized form of the data is publicly released, enabling privacy-preserving downstream analysis and reproducible research in sensitive domains. In recent years, various approaches have been proposed for achieving privacy-preserving high-dimensional data generation by private training on top of deep neural networks. In this paper, we present a novel unified view that systematizes these approaches. Our view provides a joint design space for systematically deriving methods that cater to different use cases. We then discuss the strengths, limitations, and inherent correlations between different approaches, aiming to shed light on crucial aspects and inspire future research. We conclude by presenting potential paths forward for the field of DP data generation, with the aim of steering the community toward making the next important steps in advancing privacy-preserving learning.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2869800232</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2869800232</sourcerecordid><originalsourceid>FETCH-proquest_journals_28698002323</originalsourceid><addsrcrecordid>eNqNjbsKwjAUQIMgWLT_cMG5UBNb61isj0VwsK4l0Bu5JSQ1SSv-vR38AKcznANnxiIuxCYptpwvWOx9l6Ypz3c8y0TEyhJqQ4qwhQfhG6yCipRChyaQ1PoDN0ejDAgVYg9nNOhkoBHhalvUZJ4rNldSe4x_XLL16Xg_XJLe2deAPjSdHZyZVMOLfF9Mc8HFf9UXHOQ4zw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2869800232</pqid></control><display><type>article</type><title>A Unified View of Differentially Private Deep Generative Modeling</title><source>Publicly Available Content (ProQuest)</source><creator>Chen, Dingfan ; Kerkouche, Raouf ; Fritz, Mario</creator><creatorcontrib>Chen, Dingfan ; Kerkouche, Raouf ; Fritz, Mario</creatorcontrib><description>The availability of rich and vast data sources has greatly advanced machine learning applications in various domains. However, data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing. Overcoming these obstacles in compliance with privacy considerations is key for technological progress in many real-world application scenarios that involve privacy sensitive data. Differentially private (DP) data publishing provides a compelling solution, where only a sanitized form of the data is publicly released, enabling privacy-preserving downstream analysis and reproducible research in sensitive domains. In recent years, various approaches have been proposed for achieving privacy-preserving high-dimensional data generation by private training on top of deep neural networks. In this paper, we present a novel unified view that systematizes these approaches. Our view provides a joint design space for systematically deriving methods that cater to different use cases. We then discuss the strengths, limitations, and inherent correlations between different approaches, aiming to shed light on crucial aspects and inspire future research. We conclude by presenting potential paths forward for the field of DP data generation, with the aim of steering the community toward making the next important steps in advancing privacy-preserving learning.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Machine learning ; Privacy ; Steering</subject><ispartof>arXiv.org, 2023-09</ispartof><rights>2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (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>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2869800232?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25753,37012,44590</link.rule.ids></links><search><creatorcontrib>Chen, Dingfan</creatorcontrib><creatorcontrib>Kerkouche, Raouf</creatorcontrib><creatorcontrib>Fritz, Mario</creatorcontrib><title>A Unified View of Differentially Private Deep Generative Modeling</title><title>arXiv.org</title><description>The availability of rich and vast data sources has greatly advanced machine learning applications in various domains. However, data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing. Overcoming these obstacles in compliance with privacy considerations is key for technological progress in many real-world application scenarios that involve privacy sensitive data. Differentially private (DP) data publishing provides a compelling solution, where only a sanitized form of the data is publicly released, enabling privacy-preserving downstream analysis and reproducible research in sensitive domains. In recent years, various approaches have been proposed for achieving privacy-preserving high-dimensional data generation by private training on top of deep neural networks. In this paper, we present a novel unified view that systematizes these approaches. Our view provides a joint design space for systematically deriving methods that cater to different use cases. We then discuss the strengths, limitations, and inherent correlations between different approaches, aiming to shed light on crucial aspects and inspire future research. We conclude by presenting potential paths forward for the field of DP data generation, with the aim of steering the community toward making the next important steps in advancing privacy-preserving learning.</description><subject>Artificial neural networks</subject><subject>Machine learning</subject><subject>Privacy</subject><subject>Steering</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNjbsKwjAUQIMgWLT_cMG5UBNb61isj0VwsK4l0Bu5JSQ1SSv-vR38AKcznANnxiIuxCYptpwvWOx9l6Ypz3c8y0TEyhJqQ4qwhQfhG6yCipRChyaQ1PoDN0ejDAgVYg9nNOhkoBHhalvUZJ4rNldSe4x_XLL16Xg_XJLe2deAPjSdHZyZVMOLfF9Mc8HFf9UXHOQ4zw</recordid><startdate>20230927</startdate><enddate>20230927</enddate><creator>Chen, Dingfan</creator><creator>Kerkouche, Raouf</creator><creator>Fritz, Mario</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>20230927</creationdate><title>A Unified View of Differentially Private Deep Generative Modeling</title><author>Chen, Dingfan ; Kerkouche, Raouf ; Fritz, Mario</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28698002323</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial neural networks</topic><topic>Machine learning</topic><topic>Privacy</topic><topic>Steering</topic><toplevel>online_resources</toplevel><creatorcontrib>Chen, Dingfan</creatorcontrib><creatorcontrib>Kerkouche, Raouf</creatorcontrib><creatorcontrib>Fritz, Mario</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</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>Publicly Available Content (ProQuest)</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>Chen, Dingfan</au><au>Kerkouche, Raouf</au><au>Fritz, Mario</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A Unified View of Differentially Private Deep Generative Modeling</atitle><jtitle>arXiv.org</jtitle><date>2023-09-27</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>The availability of rich and vast data sources has greatly advanced machine learning applications in various domains. However, data with privacy concerns comes with stringent regulations that frequently prohibited data access and data sharing. Overcoming these obstacles in compliance with privacy considerations is key for technological progress in many real-world application scenarios that involve privacy sensitive data. Differentially private (DP) data publishing provides a compelling solution, where only a sanitized form of the data is publicly released, enabling privacy-preserving downstream analysis and reproducible research in sensitive domains. In recent years, various approaches have been proposed for achieving privacy-preserving high-dimensional data generation by private training on top of deep neural networks. In this paper, we present a novel unified view that systematizes these approaches. Our view provides a joint design space for systematically deriving methods that cater to different use cases. We then discuss the strengths, limitations, and inherent correlations between different approaches, aiming to shed light on crucial aspects and inspire future research. We conclude by presenting potential paths forward for the field of DP data generation, with the aim of steering the community toward making the next important steps in advancing privacy-preserving learning.</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, 2023-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_2869800232
source Publicly Available Content (ProQuest)
subjects Artificial neural networks
Machine learning
Privacy
Steering
title A Unified View of Differentially Private Deep Generative Modeling
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T06%3A19%3A09IST&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=A%20Unified%20View%20of%20Differentially%20Private%20Deep%20Generative%20Modeling&rft.jtitle=arXiv.org&rft.au=Chen,%20Dingfan&rft.date=2023-09-27&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2869800232%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_28698002323%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2869800232&rft_id=info:pmid/&rfr_iscdi=true