SoK: Privacy-preserving Deep Learning with Homomorphic Encryption

Outsourced computation for neural networks allows users access to state of the art models without needing to invest in specialized hardware and know-how. The problem is that the users lose control over potentially privacy sensitive data. With homomorphic encryption (HE) computation can be performed...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-01
Main Authors: Podschwadt, Robert, Takabi, Daniel, Hu, Peizhao
Format: Article
Language:English
Subjects:
Computation
Deep learning
Encryption
Neural networks
Privacy
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 Podschwadt, Robert
Takabi, Daniel
Hu, Peizhao
description Outsourced computation for neural networks allows users access to state of the art models without needing to invest in specialized hardware and know-how. The problem is that the users lose control over potentially privacy sensitive data. With homomorphic encryption (HE) computation can be performed on encrypted data without revealing its content. In this systematization of knowledge, we take an in-depth look at approaches that combine neural networks with HE for privacy preservation. We categorize the changes to neural network models and architectures to make them computable over HE and how these changes impact performance. We find numerous challenges to HE based privacy-preserving deep learning such as computational overhead, usability, and limitations posed by the encryption schemes.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2614940430</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2614940430</sourcerecordid><originalsourceid>FETCH-proquest_journals_26149404303</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwDM73tlIIKMosS0yu1C0oSi1OLSrLzEtXcElNLVDwSU0sygPxyjNLMhQ88nOBsKggIzNZwTUvuaiyoCQzP4-HgTUtMac4lRdKczMou7mGOHsADcsvLE0tLonPyi8tygNKxRuZGZpYmhiYGBsYE6cKAHO5OXk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2614940430</pqid></control><display><type>article</type><title>SoK: Privacy-preserving Deep Learning with Homomorphic Encryption</title><source>Publicly Available Content Database</source><creator>Podschwadt, Robert ; Takabi, Daniel ; Hu, Peizhao</creator><creatorcontrib>Podschwadt, Robert ; Takabi, Daniel ; Hu, Peizhao</creatorcontrib><description>Outsourced computation for neural networks allows users access to state of the art models without needing to invest in specialized hardware and know-how. The problem is that the users lose control over potentially privacy sensitive data. With homomorphic encryption (HE) computation can be performed on encrypted data without revealing its content. In this systematization of knowledge, we take an in-depth look at approaches that combine neural networks with HE for privacy preservation. We categorize the changes to neural network models and architectures to make them computable over HE and how these changes impact performance. We find numerous challenges to HE based privacy-preserving deep learning such as computational overhead, usability, and limitations posed by the encryption schemes.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Computation ; Deep learning ; Encryption ; Neural networks ; Privacy</subject><ispartof>arXiv.org, 2022-01</ispartof><rights>2022. This work is published under http://creativecommons.org/licenses/by/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>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2614940430?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>776,780,25732,36991,44569</link.rule.ids></links><search><creatorcontrib>Podschwadt, Robert</creatorcontrib><creatorcontrib>Takabi, Daniel</creatorcontrib><creatorcontrib>Hu, Peizhao</creatorcontrib><title>SoK: Privacy-preserving Deep Learning with Homomorphic Encryption</title><title>arXiv.org</title><description>Outsourced computation for neural networks allows users access to state of the art models without needing to invest in specialized hardware and know-how. The problem is that the users lose control over potentially privacy sensitive data. With homomorphic encryption (HE) computation can be performed on encrypted data without revealing its content. In this systematization of knowledge, we take an in-depth look at approaches that combine neural networks with HE for privacy preservation. We categorize the changes to neural network models and architectures to make them computable over HE and how these changes impact performance. We find numerous challenges to HE based privacy-preserving deep learning such as computational overhead, usability, and limitations posed by the encryption schemes.</description><subject>Computation</subject><subject>Deep learning</subject><subject>Encryption</subject><subject>Neural networks</subject><subject>Privacy</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRwDM73tlIIKMosS0yu1C0oSi1OLSrLzEtXcElNLVDwSU0sygPxyjNLMhQ88nOBsKggIzNZwTUvuaiyoCQzP4-HgTUtMac4lRdKczMou7mGOHsADcsvLE0tLonPyi8tygNKxRuZGZpYmhiYGBsYE6cKAHO5OXk</recordid><startdate>20220101</startdate><enddate>20220101</enddate><creator>Podschwadt, Robert</creator><creator>Takabi, Daniel</creator><creator>Hu, Peizhao</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>20220101</creationdate><title>SoK: Privacy-preserving Deep Learning with Homomorphic Encryption</title><author>Podschwadt, Robert ; Takabi, Daniel ; Hu, Peizhao</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26149404303</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computation</topic><topic>Deep learning</topic><topic>Encryption</topic><topic>Neural networks</topic><topic>Privacy</topic><toplevel>online_resources</toplevel><creatorcontrib>Podschwadt, Robert</creatorcontrib><creatorcontrib>Takabi, Daniel</creatorcontrib><creatorcontrib>Hu, Peizhao</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 UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Databases</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest Engineering Database</collection><collection>Publicly Available Content Database</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>Podschwadt, Robert</au><au>Takabi, Daniel</au><au>Hu, Peizhao</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>SoK: Privacy-preserving Deep Learning with Homomorphic Encryption</atitle><jtitle>arXiv.org</jtitle><date>2022-01-01</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Outsourced computation for neural networks allows users access to state of the art models without needing to invest in specialized hardware and know-how. The problem is that the users lose control over potentially privacy sensitive data. With homomorphic encryption (HE) computation can be performed on encrypted data without revealing its content. In this systematization of knowledge, we take an in-depth look at approaches that combine neural networks with HE for privacy preservation. We categorize the changes to neural network models and architectures to make them computable over HE and how these changes impact performance. We find numerous challenges to HE based privacy-preserving deep learning such as computational overhead, usability, and limitations posed by the encryption schemes.</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, 2022-01
issn 2331-8422
language eng
recordid cdi_proquest_journals_2614940430
source Publicly Available Content Database
subjects Computation
Deep learning
Encryption
Neural networks
Privacy
title SoK: Privacy-preserving Deep Learning with Homomorphic Encryption
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T23%3A12%3A35IST&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=SoK:%20Privacy-preserving%20Deep%20Learning%20with%20Homomorphic%20Encryption&rft.jtitle=arXiv.org&rft.au=Podschwadt,%20Robert&rft.date=2022-01-01&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2614940430%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_26149404303%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2614940430&rft_id=info:pmid/&rfr_iscdi=true