Privacy-Preserving Deep Learning Based on Multiparty Secure Computation: A Survey

Deep learning (DL) has demonstrated superior success in various of applications, such as image classification, speech recognition, and anomalous detection. The unprecedented performance gain of DL largely depends on tremendous training data, high-performance computation resources, and well-designed...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE internet of things journal Ročník 8; číslo 13; s. 10412 - 10429
Hlavní autoři: Zhang, Qiao, Xin, Chunsheng, Wu, Hongyi
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.07.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:2327-4662, 2327-4662
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Deep learning (DL) has demonstrated superior success in various of applications, such as image classification, speech recognition, and anomalous detection. The unprecedented performance gain of DL largely depends on tremendous training data, high-performance computation resources, and well-designed model structures. However, privacy concerns raise from such necessities. First, as the training data are usually distributed among multiple parties, directly exposing and collecting such large amount of data could violate the laws especially for private information, such as personal identities, medical records, and financial profiles. Second, locally deploying advantageous computation resources is costly for individual party having partial data. Third, direct release of well-trained model parameters threatens the information about training data or the intellectual property of model owners. Therefore, individual party prefers outsourcing computation (data) in a secure way to powerful cloud servers such as Microsoft Azure, and how to enable the cloud servers to perform DL algorithms without revealing data owners' private information and model owners' valuable parameters is emerging as an urgent task, which is termed as privacy-preserving (outsourcing) DL. In this article, we review the state-of-the-art researches in privacy-preserving DL based on multiparty secure computation with data encryption and summarize these techniques in both training phase and inference phase. Specifically, we categorize the techniques with respect to the linear and nonlinear computations, which are the two basic building blocks in DL. Following a comprehensive overview of each research scheme, we present primary technical hurdles needed to be addressed and discuss several promising directions for future research.
AbstractList Deep learning (DL) has demonstrated superior success in various of applications, such as image classification, speech recognition, and anomalous detection. The unprecedented performance gain of DL largely depends on tremendous training data, high-performance computation resources, and well-designed model structures. However, privacy concerns raise from such necessities. First, as the training data are usually distributed among multiple parties, directly exposing and collecting such large amount of data could violate the laws especially for private information, such as personal identities, medical records, and financial profiles. Second, locally deploying advantageous computation resources is costly for individual party having partial data. Third, direct release of well-trained model parameters threatens the information about training data or the intellectual property of model owners. Therefore, individual party prefers outsourcing computation (data) in a secure way to powerful cloud servers such as Microsoft Azure, and how to enable the cloud servers to perform DL algorithms without revealing data owners’ private information and model owners’ valuable parameters is emerging as an urgent task, which is termed as privacy-preserving (outsourcing) DL. In this article, we review the state-of-the-art researches in privacy-preserving DL based on multiparty secure computation with data encryption and summarize these techniques in both training phase and inference phase. Specifically, we categorize the techniques with respect to the linear and nonlinear computations, which are the two basic building blocks in DL. Following a comprehensive overview of each research scheme, we present primary technical hurdles needed to be addressed and discuss several promising directions for future research.
Author Wu, Hongyi
Xin, Chunsheng
Zhang, Qiao
Author_xml – sequence: 1
  givenname: Qiao
  orcidid: 0000-0002-7752-0528
  surname: Zhang
  fullname: Zhang, Qiao
  email: qzhan002@odu.edu
  organization: School of Cybersecurity and the Department of Electrical and Computer Engineering, Old Dominion University, Norfolk, VA, USA
– sequence: 2
  givenname: Chunsheng
  orcidid: 0000-0001-5575-2849
  surname: Xin
  fullname: Xin, Chunsheng
  email: cxin@odu.edu
  organization: School of Cybersecurity and the Department of Electrical and Computer Engineering, Old Dominion University, Norfolk, VA, USA
– sequence: 3
  givenname: Hongyi
  surname: Wu
  fullname: Wu, Hongyi
  email: h1wu@odu.edu
  organization: School of Cybersecurity and the Department of Electrical and Computer Engineering, Old Dominion University, Norfolk, VA, USA
BookMark eNp9kE1Lw0AQhhdRsNb-APGy4Dl1P5JN4q3Wr0qlldbzskknsqVN4u6mkH_vhhQRDzKHmWHmeWd4L9BpWZWA0BUlY0pJevs6W6zHjDA65iRKBE9O0IBxFgehEOz0V32ORtZuCSEei2gqBuh9afRB5W2wNGDBHHT5iR8AajwHZcquu1cWNrgq8Vuzc7pWxrV4BXljAE-rfd045XRV3uEJXjXmAO0lOivUzsLomIfo4-lxPX0J5ovn2XQyD3KWcheEipMsUiSGrBAR-EhFlBEWJzTiIhExpzTNFYQCsqTYpCoLIQE_Zhz8nPIhuul1a1N9NWCd3FaNKf1JyaIwZF7OHxqiuN_KTWWtgULmuv_YGaV3khLZWSg7C2VnoTxa6En6h6yN3ivT_stc94wGgJ_9lPtPBOHfUFZ9Lw
CODEN IITJAU
CitedBy_id crossref_primary_10_1109_JIOT_2025_3540465
crossref_primary_10_3390_foods13213391
crossref_primary_10_1007_s11831_025_10355_z
crossref_primary_10_1109_ACCESS_2025_3561721
crossref_primary_10_1109_JIOT_2025_3555026
crossref_primary_10_1145_3703452
crossref_primary_10_1109_ACCESS_2025_3557228
crossref_primary_10_1109_TETCI_2024_3523771
crossref_primary_10_1145_3708505
crossref_primary_10_32604_cmes_2024_048932
crossref_primary_10_1016_j_compeleceng_2024_109792
crossref_primary_10_1016_j_ject_2025_08_001
crossref_primary_10_1109_ACCESS_2024_3381611
crossref_primary_10_1016_j_comnet_2024_110641
crossref_primary_10_1109_COMST_2021_3108618
crossref_primary_10_1109_JIOT_2024_3415499
crossref_primary_10_1016_j_dcan_2025_04_009
Cites_doi 10.1109/TIP.2017.2670780
10.1080/15265161.2010.494215
10.1109/JIOT.2018.2838574
10.1145/2508859.2516738
10.1145/3133956.3134056
10.1007/978-3-642-40041-4_5
10.1109/SFCS.1986.25
10.1145/2487726.2488368
10.1109/SP.2017.15
10.1371/journal.pone.0168054
10.1109/SP.2019.00045
10.1007/978-3-319-57959-7
10.1007/s00779-016-0963-3
10.1109/SP40000.2020.00092
10.1515/popets-2018-0024
10.1016/j.ins.2018.12.015
10.1109/FOCS.2010.12
10.1109/MSP.2012.2205597
10.1145/3133956.3134077
10.1109/TII.2018.2875149
10.1109/TII.2018.2853676
10.1145/359168.359176
10.1109/TASL.2011.2134090
10.1109/SP.2013.39
10.1145/3319535.3339819
10.1109/ICDE48307.2020.00152
10.1007/978-3-642-20465-4_4
10.1145/3373376.3378523
10.1145/3065913.3065915
10.1145/3310273.3323047
10.1109/SP.2017.12
10.1016/j.clsr.2013.07.010
10.1145/3319535.3363207
10.14722/ndss.2020.23005
10.1145/2647868.2654889
10.1007/978-3-540-70583-3_40
10.1145/3411501.3419425
10.1145/3195970.3196023
10.1109/COMST.2018.2844341
10.1145/2633600
10.1561/3300000019
10.1109/JPROC.2020.2976475
10.1145/3372297.3417872
10.1109/MSEC.2018.2888775
10.1007/3-540-48910-X_16
10.1109/TDSC.2019.2913362
10.1561/0400000042
10.1109/TPAMI.2019.2944377
10.1109/EuroSP.2016.28
10.1145/100216.100287
10.1109/JIOT.2018.2875244
10.1145/1077464.1077466
10.1007/978-3-319-70694-8_15
10.1006/jcom.1998.0476
10.1145/3007787.3001163
10.1109/IEMBS.2006.260060
10.1109/HPCA47549.2020.00030
10.1109/SP.2017.41
10.1109/FCCM48280.2020.00037
10.1109/CVPR.2016.90
10.2478/popets-2019-0035
10.1007/978-3-540-45146-4_9
10.1145/3243734.3243837
10.1016/j.neucom.2019.11.041
10.1109/TNNLS.2018.2886017
10.1109/ICASSP.2013.6639344
10.1007/978-3-642-32009-5_50
10.24963/ijcai.2019/671
10.1007/978-3-540-79228-4_1
10.1109/CVPR.2015.7298594
10.1145/2810103.2813677
10.1109/ICDCS.2018.00178
10.1109/CVPR.2017.243
10.1145/2608628.2608664
10.1145/257874.257896
10.24963/ijcai.2018/547
10.1007/978-3-642-40994-3_25
10.1109/TNSE.2018.2846736
10.1145/3394658
10.1109/CVPR.2009.5206848
10.1007/s00145-011-9107-0
10.1109/TIT.1985.1057074
10.1007/s10623-012-9720-4
10.1007/978-3-319-22846-4_11
10.1145/3196494.3196522
10.1145/1536414.1536440
10.1145/3372297.3417274
10.1007/978-3-030-30619-9_4
10.1007/978-3-319-70972-7_27
10.1109/JIOT.2017.2720635
10.14722/ndss.2015.23241
10.1109/SP.2019.00028
10.1007/978-3-540-30576-7_18
10.1109/TIFS.2020.2988132
10.1145/2976749.2978331
10.1145/3158363
10.1145/28395.28420
10.1109/ACCESS.2018.2830661
10.1007/978-3-662-46803-6_8
10.1109/ICMLA.2015.152
10.1145/2948618.2954331
10.1145/3338469.3358944
10.1109/SFCS.1982.38
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/JIOT.2021.3058638
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList Computer and Information Systems Abstracts

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2327-4662
EndPage 10429
ExternalDocumentID 10_1109_JIOT_2021_3058638
9352960
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation
  grantid: CNS-1828593; OAC-1829771; EEC-1840458; CNS-1950704
  funderid: 10.13039/100000001
– fundername: Office of Naval Research
  grantid: N00014-20-1-2065
  funderid: 10.13039/100000006
– fundername: Commonwealth Cyber Initiative, an Investment in the Advancement of Cyber Research and Development, Innovation and Workforce Development
GroupedDBID 0R~
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABJNI
ABQJQ
ABVLG
AGQYO
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
IFIPE
IPLJI
JAVBF
M43
OCL
PQQKQ
RIA
RIE
AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c293t-4a30b5a07ebf65e5e5965b027815368673119cae46eb8fd9ab4e8e27823e36813
IEDL.DBID RIE
ISICitedReferencesCount 27
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000665207100017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2327-4662
IngestDate Sun Nov 30 04:45:06 EST 2025
Tue Nov 18 21:12:15 EST 2025
Sat Nov 29 06:16:56 EST 2025
Wed Aug 27 02:27:01 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 13
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c293t-4a30b5a07ebf65e5e5965b027815368673119cae46eb8fd9ab4e8e27823e36813
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-7752-0528
0000-0001-5575-2849
PQID 2544296529
PQPubID 2040421
PageCount 18
ParticipantIDs proquest_journals_2544296529
crossref_citationtrail_10_1109_JIOT_2021_3058638
ieee_primary_9352960
crossref_primary_10_1109_JIOT_2021_3058638
PublicationCentury 2000
PublicationDate 2021-07-01
PublicationDateYYYYMMDD 2021-07-01
PublicationDate_xml – month: 07
  year: 2021
  text: 2021-07-01
  day: 01
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE internet of things journal
PublicationTitleAbbrev JIoT
PublicationYear 2021
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref57
(ref96) 2020
ref59
boneh (ref53) 2005
liu (ref48) 2020
ref58
wagh (ref132) 2018
ref55
elgamal (ref52) 1985; 31
ref169
ref54
kozlov (ref181) 2020
(ref99) 2020
koti (ref129) 2020
liu (ref135) 2020
zhu (ref139) 2020
bourse (ref167) 2017
(ref102) 2020
ref175
ref51
ref50
ref173
ref174
ref172
biondo (ref119) 2018
ref45
(ref168) 2020
dahl (ref189) 2018
ref47
(ref70) 2020
ref41
ref43
(ref30) 2018
(ref107) 2020
ref180
ref7
ref4
simonyan (ref9) 2014
dwork (ref44) 2006
ref5
ref40
ref187
ref184
(ref73) 2020
ref185
ref182
ref183
banerjee (ref156) 2020
ref35
(ref61) 2020
ref34
wagh (ref121) 2020
ref37
(ref71) 2020
ref36
hashemi (ref157) 2020
(ref104) 2020
froelicher (ref150) 2020
ref33
ref147
ref38
dwork (ref42) 2014; 9
(ref108) 2020
(ref31) 2019
aloufi (ref49) 2020
(ref94) 2020
(ref170) 2020
ref153
ref154
ref152
han (ref179) 2015
ref24
ref23
(ref67) 2020
ref26
badawi (ref151) 2018
morshed (ref176) 2020
ref25
ref20
ref22
ref21
ioffe (ref163) 2015
fan (ref56) 2012
chabanne (ref155) 2017
ref27
evans (ref160) 2017; 2
(ref103) 2020
(ref95) 2020
bashar (ref6) 2019; 1
tramèr (ref123) 2016
han (ref178) 2015
ref166
juvekar (ref76) 2018
ref164
(ref109) 2020
(ref32) 2019
(ref171) 2020
mirshghallah (ref39) 2020
gilad-bachrach (ref142) 2016
ref161
tramèr (ref158) 2018
ref13
ref12
ref128
ref15
ref14
ref126
ref127
zhu (ref122) 2020
ref124
ref11
ref125
ref10
snyder (ref85) 2014
zhao (ref186) 2020
ref17
ref16
ref19
ref18
ref133
ref93
(ref72) 2020
ref134
reagen (ref141) 2020
ref92
ref131
ref130
ref91
riazi (ref138) 2019
ref137
ref86
(ref62) 2020
ref88
ref87
(ref29) 1996
goldreich (ref89) 2009
aggarwal (ref136) 2020
(ref65) 2020
wang (ref162) 2016
li (ref145) 2020
ref144
ref82
(ref116) 2020
abadi (ref165) 2016
ref81
ref84
reis (ref177) 2020
ref83
(ref101) 2020
ref140
zhang (ref146) 2019
ref80
ref78
adshead (ref3) 2014; 9
lecun (ref46) 1990
(ref68) 2020
ref77
chou (ref143) 2018
brasser (ref117) 2017
ref2
ref1
ref191
ref192
ref190
krizhevsky (ref8) 2012
bian (ref149) 2020
(ref74) 2020
ref111
(ref100) 2020
ref112
(ref97) 2020
ref69
ref118
ref64
ref115
ref66
ref113
ref114
ryffel (ref188) 2018
hunt (ref159) 2018
lou (ref148) 2020
(ref75) 2020
keller (ref110) 2020
(ref98) 2020
mohassel (ref105) 2018
ref60
beaver (ref90) 1991
goldman (ref28) 2020
(ref106) 2020
ref120
mishra (ref79) 2020
(ref63) 2020
References_xml – ident: ref13
  doi: 10.1109/TIP.2017.2670780
– ident: ref24
  doi: 10.1080/15265161.2010.494215
– year: 2020
  ident: ref94
– ident: ref17
  doi: 10.1109/JIOT.2018.2838574
– ident: ref161
  doi: 10.1145/2508859.2516738
– ident: ref131
  doi: 10.1145/3133956.3134056
– ident: ref66
  doi: 10.1007/978-3-642-40041-4_5
– year: 2020
  ident: ref104
– ident: ref120
  doi: 10.1109/SFCS.1986.25
– year: 2020
  ident: ref73
– ident: ref112
  doi: 10.1145/2487726.2488368
– ident: ref92
  doi: 10.1109/SP.2017.15
– ident: ref172
  doi: 10.1371/journal.pone.0168054
– year: 2020
  ident: ref107
– ident: ref153
  doi: 10.1109/SP.2019.00045
– ident: ref26
  doi: 10.1007/978-3-319-57959-7
– year: 2020
  ident: ref181
  publication-title: Neural network compression framework for fast model inference
– ident: ref21
  doi: 10.1007/s00779-016-0963-3
– year: 2020
  ident: ref116
– ident: ref187
  doi: 10.1109/SP40000.2020.00092
– ident: ref154
  doi: 10.1515/popets-2018-0024
– ident: ref152
  doi: 10.1016/j.ins.2018.12.015
– year: 2019
  ident: ref146
  publication-title: CHEETAH An ultra-fast approximation-free and privacy-preserved neural network framework based on joint obscure linear and nonlinear computations
– start-page: 201
  year: 2016
  ident: ref142
  article-title: CryptoNets: Applying neural networks to encrypted data with high throughput and accuracy
  publication-title: Proc Int Conf Mach Learn
– year: 2020
  ident: ref39
  publication-title: Privacy in deep learning A survey
– ident: ref43
  doi: 10.1109/FOCS.2010.12
– ident: ref10
  doi: 10.1109/MSP.2012.2205597
– start-page: 9403
  year: 2020
  ident: ref149
  article-title: ENSEI: Efficient secure inference via frequency-domain homomorphic convolution for privacy-preserving visual recognition
  publication-title: Proc IEEE Conf Comput Vis and Pattern Recog
– year: 2014
  ident: ref85
  article-title: Yao's garbled circuits: Recent directions and implementations
  publication-title: Literature Review
– ident: ref33
  doi: 10.1145/3133956.3134077
– start-page: 1213
  year: 2018
  ident: ref119
  article-title: The guard's dilemma: Efficient code-reuse attacks against Intel SGX
  publication-title: Proc 27th USENIX Security Symp
– year: 2017
  ident: ref167
  article-title: Fast homomorphic evaluation of deep discretized neural networks
– volume: 9
  year: 2014
  ident: ref3
  publication-title: Data set to grow 10-fold by 2020 as internet of things takes off
– year: 2009
  ident: ref89
  publication-title: Foundations of Cryptography Volume 2 Basic Applications
– ident: ref4
  doi: 10.1109/TII.2018.2875149
– ident: ref5
  doi: 10.1109/TII.2018.2853676
– year: 2020
  ident: ref136
  publication-title: SOTERIA In search of efficient neural networks for private inference
– ident: ref88
  doi: 10.1145/359168.359176
– start-page: 396
  year: 1990
  ident: ref46
  article-title: Handwritten digit recognition with a back-propagation network
  publication-title: Advances in neural information processing systems
– year: 2018
  ident: ref159
  publication-title: Chiron Privacy-preserving machine learning as a service
– ident: ref11
  doi: 10.1109/TASL.2011.2134090
– ident: ref82
  doi: 10.1109/SP.2013.39
– ident: ref84
  doi: 10.1145/3319535.3339819
– ident: ref147
  doi: 10.1109/ICDE48307.2020.00152
– ident: ref69
  doi: 10.1007/978-3-642-20465-4_4
– year: 2020
  ident: ref170
– ident: ref175
  doi: 10.1145/3373376.3378523
– year: 2020
  ident: ref61
– ident: ref118
  doi: 10.1145/3065913.3065915
– ident: ref191
  doi: 10.1145/3310273.3323047
– ident: ref128
  doi: 10.1109/SP.2017.12
– year: 2016
  ident: ref162
  publication-title: EMP-toolkit Efficient multiparty computation toolkit
– ident: ref27
  doi: 10.1016/j.clsr.2013.07.010
– ident: ref59
  doi: 10.1145/3319535.3363207
– ident: ref133
  doi: 10.14722/ndss.2020.23005
– start-page: 2505
  year: 2020
  ident: ref79
  article-title: Delphi: A cryptographic inference service for neural networks
  publication-title: Proc 29th USENIX Security Symp
– ident: ref47
  doi: 10.1145/2647868.2654889
– year: 2014
  ident: ref9
  publication-title: Very Deep Convolutional Networks for Large-scale Image Recognition
– start-page: 1501
  year: 2019
  ident: ref138
  article-title: XONN XNOR-based oblivious deep neural network inference
  publication-title: Proc 28th USENIX Security Symp
– ident: ref80
  doi: 10.1007/978-3-540-70583-3_40
– year: 2020
  ident: ref100
– year: 2020
  ident: ref63
– year: 2020
  ident: ref129
  publication-title: SWIFT Super-fast and robust privacy-preserving machine learning
– year: 2020
  ident: ref148
  publication-title: AutoPrivacy Automated layer-wise parameter selection for secure neural network inference
– year: 2018
  ident: ref132
  article-title: Securenn: Efficient and private neural network training
– ident: ref192
  doi: 10.1145/3411501.3419425
– ident: ref137
  doi: 10.1145/3195970.3196023
– ident: ref16
  doi: 10.1109/COMST.2018.2844341
– year: 2018
  ident: ref158
  publication-title: Slalom Fast verifiable and private execution of neural networks in trusted hardware
– year: 2015
  ident: ref178
  publication-title: Deep compression Compressing deep neural networks with pruning trained quantization and huffman coding
– ident: ref64
  doi: 10.1145/2633600
– year: 2018
  ident: ref30
  publication-title: Uber to Pay 148 Million Penalty to Settle 2016 Data Breach
– year: 2019
  ident: ref32
  publication-title: France Fines Google 57 Million for Breaking Europe's Strict New Privacy Rules
– year: 2020
  ident: ref67
– volume: 2
  start-page: 70
  year: 2017
  ident: ref160
  article-title: A pragmatic introduction to secure multi-party computation
  publication-title: Foundations and Trends in Privacy and Security
  doi: 10.1561/3300000019
– year: 2020
  ident: ref97
– year: 2020
  ident: ref28
  article-title: An introduction to the California consumer privacy act (CCPA)
  publication-title: Santa Clara Univ Legal Studies Research Paper
– ident: ref45
  doi: 10.1109/JPROC.2020.2976475
– year: 2020
  ident: ref110
  article-title: MP-SPDZ: A versatile framework for multi-party computation
  doi: 10.1145/3372297.3417872
– start-page: 265
  year: 2006
  ident: ref44
  article-title: Calibrating noise to sensitivity in private data analysis
  publication-title: Proc Theory Cryptogr Conf
– year: 2020
  ident: ref71
– year: 2020
  ident: ref121
  publication-title: Falcon Honest-majority maliciously secure framework for private deep learning
– ident: ref37
  doi: 10.1109/MSEC.2018.2888775
– ident: ref51
  doi: 10.1007/3-540-48910-X_16
– year: 2020
  ident: ref176
  publication-title: CPU and GPU accelerated fully homomorphic encryption
– year: 2020
  ident: ref102
– year: 2020
  ident: ref95
– ident: ref134
  doi: 10.1109/TDSC.2019.2913362
– year: 2020
  ident: ref139
  article-title: Practical MPC+FHE with applications in secure multi-partyneural network evaluation
– year: 2020
  ident: ref65
– volume: 9
  start-page: 211
  year: 2014
  ident: ref42
  article-title: The algorithmic foundations of differential privacy
  publication-title: Found Trends Theor Comput Sci
  doi: 10.1561/0400000042
– ident: ref14
  doi: 10.1109/TPAMI.2019.2944377
– ident: ref115
  doi: 10.1109/EuroSP.2016.28
– ident: ref81
  doi: 10.1145/100216.100287
– start-page: 1651
  year: 2018
  ident: ref76
  article-title: GAZELLE: A low latency framework for secure neural network inference
  publication-title: Proc 27th USENIX Security Symp
– year: 2020
  ident: ref49
  article-title: Computing blindfolded on data homomorphically encrypted under multiple keys: An extended survey
– year: 2020
  ident: ref156
  publication-title: SESAME Software defined enclaves to secure inference accelerators with multi-tenant execution
– ident: ref2
  doi: 10.1109/JIOT.2018.2875244
– ident: ref184
  doi: 10.1145/1077464.1077466
– year: 2020
  ident: ref150
  publication-title: Scalable privacy-preserving distributed learning
– year: 2020
  ident: ref99
– ident: ref57
  doi: 10.1007/978-3-319-70694-8_15
– year: 2020
  ident: ref141
  publication-title: Cheetah Optimizing and accelerating homomorphic encryption for private inference
– ident: ref185
  doi: 10.1006/jcom.1998.0476
– ident: ref180
  doi: 10.1145/3007787.3001163
– year: 2020
  ident: ref109
– ident: ref23
  doi: 10.1109/IEMBS.2006.260060
– year: 2020
  ident: ref171
– ident: ref182
  doi: 10.1109/HPCA47549.2020.00030
– ident: ref124
  doi: 10.1109/SP.2017.41
– ident: ref174
  doi: 10.1109/FCCM48280.2020.00037
– ident: ref19
  doi: 10.1109/CVPR.2016.90
– year: 2018
  ident: ref143
  publication-title: Faster CryptoNets Leveraging sparsity for real-world encrypted inference
– ident: ref35
  doi: 10.2478/popets-2019-0035
– ident: ref87
  doi: 10.1007/978-3-540-45146-4_9
– ident: ref50
  doi: 10.1145/3243734.3243837
– ident: ref40
  doi: 10.1016/j.neucom.2019.11.041
– ident: ref125
  doi: 10.1109/TNNLS.2018.2886017
– ident: ref12
  doi: 10.1109/ICASSP.2013.6639344
– volume: 1
  start-page: 73
  year: 2019
  ident: ref6
  article-title: Survey on evolving deep learning neural network architectures
  publication-title: J Artif Intell
– start-page: 420
  year: 1991
  ident: ref90
  article-title: Efficient multiparty protocols using circuit randomization
  publication-title: Proc Annu Int Cryptol Conf
– ident: ref55
  doi: 10.1007/978-3-642-32009-5_50
– ident: ref140
  doi: 10.24963/ijcai.2019/671
– ident: ref41
  doi: 10.1007/978-3-540-79228-4_1
– ident: ref18
  doi: 10.1109/CVPR.2015.7298594
– start-page: 1135
  year: 2015
  ident: ref179
  article-title: Learning both weights and connections for efficient neural network
  publication-title: Advances in neural information processing systems
– year: 2020
  ident: ref75
– year: 2020
  ident: ref106
– ident: ref34
  doi: 10.1145/2810103.2813677
– year: 2020
  ident: ref62
– ident: ref15
  doi: 10.1109/ICDCS.2018.00178
– year: 2018
  ident: ref188
  publication-title: A generic framework for privacy preserving deep learning
– ident: ref164
  doi: 10.1109/CVPR.2017.243
– ident: ref183
  doi: 10.1145/2608628.2608664
– ident: ref22
  doi: 10.1145/257874.257896
– ident: ref144
  doi: 10.24963/ijcai.2018/547
– year: 2020
  ident: ref177
  publication-title: Computing-in-memory for performance and energy efficient homomorphic encryption
– ident: ref126
  doi: 10.1007/978-3-642-40994-3_25
– ident: ref25
  doi: 10.1109/TNSE.2018.2846736
– year: 2018
  ident: ref189
  publication-title: Private machine learning in TensorFlow using secure computation
– ident: ref60
  doi: 10.1145/3394658
– start-page: 601
  year: 2016
  ident: ref123
  article-title: Stealing machine learning models via prediction APIs
  publication-title: Proc 25th Usenix Security Symp
– start-page: 265
  year: 2016
  ident: ref165
  article-title: TensorFlow: A system for large-scale machine learning
  publication-title: Proc 12th USENIX Symp Oper Syst Design Implement
– year: 2012
  ident: ref56
  article-title: Somewhat practical fully homomorphic encryption
– ident: ref169
  doi: 10.1109/CVPR.2009.5206848
– ident: ref78
  doi: 10.1007/s00145-011-9107-0
– volume: 31
  start-page: 469
  year: 1985
  ident: ref52
  article-title: A public key cryptosystem and a signature scheme based on discrete logarithms
  publication-title: IEEE Trans Inf Theory
  doi: 10.1109/TIT.1985.1057074
– ident: ref58
  doi: 10.1007/s10623-012-9720-4
– year: 2020
  ident: ref48
  publication-title: MPC-enabled privacy-preserving neural network training against malicious attack
– start-page: 8705
  year: 2020
  ident: ref145
  article-title: FALCON: A fourier transform based approach for fast and secure convolutional neural network predictions
  publication-title: Proc IEEE Conf Comput Vis and Pattern Recog
– start-page: 35
  year: 2018
  ident: ref105
  article-title: ABY3: A mixed protocol framework for machine learning
  publication-title: Proc ACM SIGSAC Conf Comput Commun Security
– year: 2020
  ident: ref74
– year: 2020
  ident: ref157
  publication-title: DarKnight A data privacy scheme for training and inference of deep neural networks
– ident: ref114
  doi: 10.1007/978-3-319-22846-4_11
– year: 2020
  ident: ref108
– year: 2020
  ident: ref103
– ident: ref130
  doi: 10.1145/3196494.3196522
– ident: ref54
  doi: 10.1145/1536414.1536440
– ident: ref173
  doi: 10.1145/3372297.3417274
– start-page: 1097
  year: 2012
  ident: ref8
  article-title: ImageNet classification with deep convolutional neural networks
  publication-title: Advances in neural information processing systems
– ident: ref36
  doi: 10.1007/978-3-030-30619-9_4
– year: 2015
  ident: ref163
  publication-title: Batch Normalization Accelerating Deep Network Training by Reducing Internal Covariate Shift
– ident: ref113
  doi: 10.1007/978-3-319-70972-7_27
– year: 2020
  ident: ref68
– ident: ref1
  doi: 10.1109/JIOT.2017.2720635
– ident: ref166
  doi: 10.14722/ndss.2015.23241
– year: 2020
  ident: ref98
– start-page: 11
  year: 2017
  ident: ref117
  article-title: Software grand exposure: SGX cache attacks are practical
  publication-title: Proc 11th USENIX Workshop Offensive Technol
– year: 2020
  ident: ref72
– year: 2020
  ident: ref168
– ident: ref93
  doi: 10.1109/SP.2019.00028
– year: 2017
  ident: ref155
  article-title: Privacy-preserving classification on deep neural network
– start-page: 325
  year: 2005
  ident: ref53
  article-title: Evaluating 2-DNF formulas on ciphertexts
  publication-title: Proc Theory Cryptogr Conf
  doi: 10.1007/978-3-540-30576-7_18
– ident: ref127
  doi: 10.1109/TIFS.2020.2988132
– year: 2020
  ident: ref135
  article-title: Leia: A lightweight cryptographic neural network inference system at the edge
– year: 2020
  ident: ref101
– ident: ref91
  doi: 10.1145/2976749.2978331
– year: 2020
  ident: ref70
– ident: ref38
  doi: 10.1145/3158363
– year: 2020
  ident: ref96
– year: 2020
  ident: ref186
  publication-title: Efficient integer-arithmetic-only convolutional neural networks
– year: 2018
  ident: ref151
  publication-title: The alexnet moment for homomorphic encryption Hcnn the first homomorphic cnn on encrypted data with gpus
– year: 2019
  ident: ref31
  publication-title: Data Breach News PDPC Fines IHiS SingHealth
– ident: ref86
  doi: 10.1145/28395.28420
– ident: ref7
  doi: 10.1109/ACCESS.2018.2830661
– ident: ref83
  doi: 10.1007/978-3-662-46803-6_8
– ident: ref20
  doi: 10.1109/ICMLA.2015.152
– ident: ref111
  doi: 10.1145/2948618.2954331
– ident: ref190
  doi: 10.1145/3338469.3358944
– ident: ref77
  doi: 10.1109/SFCS.1982.38
– year: 2020
  ident: ref122
  publication-title: Hermes attack Steal DNN models with lossless inference accuracy
– year: 1996
  ident: ref29
  article-title: Health insurance portability and accountability act of 1996
  publication-title: Public Law 104-191
SSID ssj0001105196
Score 2.4097583
Snippet Deep learning (DL) has demonstrated superior success in various of applications, such as image classification, speech recognition, and anomalous detection. The...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 10412
SubjectTerms Algorithms
Cloud computing
Computational modeling
Data encryption
Data models
Data privacy
Deep learning
Deep learning (DL)
Image classification
linear and nonlinear computations
Machine learning
Mathematical models
Object recognition
Outsourcing
Parameters
Predictive models
Privacy
privacy preserving
Servers
Speech recognition
State-of-the-art reviews
Training
Title Privacy-Preserving Deep Learning Based on Multiparty Secure Computation: A Survey
URI https://ieeexplore.ieee.org/document/9352960
https://www.proquest.com/docview/2544296529
Volume 8
WOSCitedRecordID wos000665207100017&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Electronic Library (IEL)
  customDbUrl:
  eissn: 2327-4662
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001105196
  issn: 2327-4662
  databaseCode: RIE
  dateStart: 20140101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlR3LSgMxMNTiwYtVq1itkoMnMXWf2cRbfRT1UCtW6G1JsrOlINvSF_TvTbJpFRRB9hKYSVhmksxM5oXQhYKcxaB8woTKSaR1cMK9QBCuRTVLgjAUkbTNJpJulw0GvFdBV5tcGACwwWfQMkPry8_GamGeyq55aLyE2kDfShJa5mp9vaf4RhmhznHpe_z6-emlrw3AwG_pPc2oyUD5JnpsL5UfF7CVKp3a__5nD-067RG3S3bvowoUB6i27syA3UGto9fedLQUakVMhIW5DYohvgeYYFdOdYhvtfTK8LjANgN3ojfQCtu3d8DlcpZjN7iN3xbTJawO0XvnoX_3SFzzBKK0BJ-TSISejIWXgMxpDPrjNJbGz6jvOMpoEvo-VwIiCpLlGRcyAgYaHISg4X54hKrFuIBjhHMuqZdFIguVPvLM40ESMOpDImOtfwBrIG9N11S5yuKmwcVHai0Mj6eGFalhRepY0UCXmymTsqzGX8h1Q_sNoiN7AzXXzEvdwZulpuKaBmqEk99nnaIds3YZcdtE1fl0AWdoWy3no9n03O6pT_6wyTQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlR3LSgMxcCgq6MVXFeszB0_iavaVTbz5pL5qxQrelmx2VgTZltoW-vcm2bQKiiB7WchkN2RmMq_MDMC-woLHqHyPS1V4kdbBPUED6QktqnkShKGMMttsImm1-MuLaNfgcJoLg4j28hkemVcby8-7amhcZcciNFFCbaDPxlEU0Cpb68uj4ht1hLnQpU_F8c31Q0ebgIF_pKmaM5OD8k342G4qP45gK1eulv63omVYdPojOa0QvgI1LFdhadKbgThWrcNju_82kmrsmTsW5jwoX8kFYo-4gqqv5EzLr5x0S2JzcHuahMbEet-RVJ-zODshp-Rp2B_heA2ery47503PtU_wlJbhAy-SIc1iSRPMChajfgSLMxNp1Kcc4ywJfV8oiRHDjBe5kFmEHPVwEKIe98N1mCm7JW4AKUTGaB7JPFSa6TkVQRJw5mOSxVoDQd4AOtnXVLna4qbFxXtqbQwqUoOK1KAidahowMF0Sq8qrPEXcN3s_RTQbXsDtifISx3rfaSm5poe1ACbv8_ag_lm5_4uvbtu3W7BgvlPdf92G2YG_SHuwJwaDd4--ruWvj4BoC_Mew
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Privacy-Preserving+Deep+Learning+Based+on+Multiparty+Secure+Computation%3A+A+Survey&rft.jtitle=IEEE+internet+of+things+journal&rft.au=Zhang%2C+Qiao&rft.au=Xin%2C+Chunsheng&rft.au=Wu%2C+Hongyi&rft.date=2021-07-01&rft.issn=2327-4662&rft.eissn=2327-4662&rft.volume=8&rft.issue=13&rft.spage=10412&rft.epage=10429&rft_id=info:doi/10.1109%2FJIOT.2021.3058638&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JIOT_2021_3058638
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2327-4662&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2327-4662&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2327-4662&client=summon