SPOT: Structure Patching and Overlap Tweaking for Effective Pipelining in Privacy-Preserving MLaaS with Tiny Clients

Machine Learning as a Service (MLaaS) has paved the way for numerous applications for resource-limited clients, such as IoT/mobile users. However, it raises a great challenge for privacy, including both the data privacy of clients and model privacy of the server. While there have been extensive stud...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the International Conference on Distributed Computing Systems pp. 1318 - 1329
Main Authors: Xu, Xiangrui, Zhang, Qiao, Ning, Rui, Xin, Chunsheng, Wu, Hongyi
Format: Conference Proceeding
Language:English
Published: IEEE 23.07.2024
Subjects:
Computational efficiency
Data privacy
Encryption
Homomorphic Encryption
Machine learning
Machine Learning as a Service
Memory management
Mobile Computing
Mobile handsets
Neural networks
Privacy-preserving
Structure Patching
ISSN:2575-8411
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Machine Learning as a Service (MLaaS) has paved the way for numerous applications for resource-limited clients, such as IoT/mobile users. However, it raises a great challenge for privacy, including both the data privacy of clients and model privacy of the server. While there have been extensive studies on privacy-preserving MLaaS, a direct adoption of current frameworks leads to intractable efficiency bottleneck for MLaaS with resource constrained clients. In this paper, we focus on MLaaS with resource constrained clients and propose a novel privacy-preserving framework called SPOT to address a unique challenge, the memory constraint of such clients, such as IoT /mobile devices, which results in significant computation stalls at the server in privacy-preserving MLaaS. We develop 1) a novel structure patching scheme to enable independent computations for sequential inputs at the server to eliminate the computation stall, and 2) a patch overlap tweaking scheme to minimize overlapped data between adjacent patches and thus enable more efficient computation with flexible cryptographic parameters. SPOT demonstrates significant improvement on computation efficiency for MLaaS with IoT /mobile clients. Compared with the state-of-the-art framework for privacy-preserving MLaaS, SPOT achieves up to 2 × memory utilization boost and a speedup up to 3 × on computation time for modern neural networks such as ResNet and VGG.
AbstractList Machine Learning as a Service (MLaaS) has paved the way for numerous applications for resource-limited clients, such as IoT/mobile users. However, it raises a great challenge for privacy, including both the data privacy of clients and model privacy of the server. While there have been extensive studies on privacy-preserving MLaaS, a direct adoption of current frameworks leads to intractable efficiency bottleneck for MLaaS with resource constrained clients. In this paper, we focus on MLaaS with resource constrained clients and propose a novel privacy-preserving framework called SPOT to address a unique challenge, the memory constraint of such clients, such as IoT /mobile devices, which results in significant computation stalls at the server in privacy-preserving MLaaS. We develop 1) a novel structure patching scheme to enable independent computations for sequential inputs at the server to eliminate the computation stall, and 2) a patch overlap tweaking scheme to minimize overlapped data between adjacent patches and thus enable more efficient computation with flexible cryptographic parameters. SPOT demonstrates significant improvement on computation efficiency for MLaaS with IoT /mobile clients. Compared with the state-of-the-art framework for privacy-preserving MLaaS, SPOT achieves up to 2 × memory utilization boost and a speedup up to 3 × on computation time for modern neural networks such as ResNet and VGG.
Author Xu, Xiangrui
Wu, Hongyi
Xin, Chunsheng
Zhang, Qiao
Ning, Rui
Author_xml – sequence: 1
  givenname: Xiangrui
  surname: Xu
  fullname: Xu, Xiangrui
  email: xxu002@odu.edu
  organization: Old Dominion University,Department of Computer Science,Norfolk,USA
– sequence: 2
  givenname: Qiao
  surname: Zhang
  fullname: Zhang, Qiao
  email: qiaozhang@cqu.edu.cn
  organization: Chongqing University,Department of Computer Science,Chongqing,China
– sequence: 3
  givenname: Rui
  surname: Ning
  fullname: Ning, Rui
  email: rning@cs.odu.edu
  organization: Old Dominion University,Department of Computer Science,Norfolk,USA
– sequence: 4
  givenname: Chunsheng
  surname: Xin
  fullname: Xin, Chunsheng
  email: cxin@odu.edu
  organization: Old Dominion University,Department of Electrical & Computer Engineering,Norfolk,USA
– sequence: 5
  givenname: Hongyi
  surname: Wu
  fullname: Wu, Hongyi
  email: mhwu@arizona.edu
  organization: University of Arizona,Department of Electrical & Computer Engineering,Tucson,USA
BookMark eNotjNFOwjAYhavRREDeQJO-wPDvunatd2aikmBYsnlNyvZXqlhIV0Z4eyF6dXK-7-QMyZXfeiTknsGEMdAPs-K5qCToU08hzSYALM0uyFjnWnEBXEkQ-pIMUpGLRGWM3ZBh130BgFCSD0isykX9SKsY9k3cB6Slic3a-U9qfEsXPYaN2dH6gOb7DO020Km12ETXn7Zuhxvnz8J5WgbXm-aYlAE7DP2Zvs-NqejBxTWtnT_SYuPQx-6WXFuz6XD8nyPy8TKti7dkvnidFU_zxLFcxkQ3aWZ1yzkXSoE17UqvjGRtiqzNlWpypiW0KViwTDJojISc5wIBWlQrofmI3P39OkRc7oL7MeG4ZCA5A874L2-_Xk4
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICDCS60910.2024.00124
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9798350386059
EISSN 2575-8411
EndPage 1329
ExternalDocumentID 10631031
Genre orig-research
GrantInformation_xml – fundername: National Science Foundation
  grantid: OAC-2320999,CNS-2120279,IIS-2236578,CNS-2153358,DUE-2153358
  funderid: 10.13039/100000001
– fundername: National Natural Science Foundation of China
  grantid: 62302067
  funderid: 10.13039/501100001667
GroupedDBID 29G
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i176t-9c24f9d3335880fadb9ba61d2e1d788c71960d20f0f1610ca607375e00de8b593
IEDL.DBID RIE
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001304430200115&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:32:38 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i176t-9c24f9d3335880fadb9ba61d2e1d788c71960d20f0f1610ca607375e00de8b593
PageCount 12
ParticipantIDs ieee_primary_10631031
PublicationCentury 2000
PublicationDate 2024-July-23
PublicationDateYYYYMMDD 2024-07-23
PublicationDate_xml – month: 07
  year: 2024
  text: 2024-July-23
  day: 23
PublicationDecade 2020
PublicationTitle Proceedings of the International Conference on Distributed Computing Systems
PublicationTitleAbbrev ICDCS
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0005863
Score 2.3270702
Snippet Machine Learning as a Service (MLaaS) has paved the way for numerous applications for resource-limited clients, such as IoT/mobile users. However, it raises a...
SourceID ieee
SourceType Publisher
StartPage 1318
SubjectTerms Computational efficiency
Data privacy
Encryption
Homomorphic Encryption
Machine learning
Machine Learning as a Service
Memory management
Mobile Computing
Mobile handsets
Neural networks
Privacy-preserving
Structure Patching
Title SPOT: Structure Patching and Overlap Tweaking for Effective Pipelining in Privacy-Preserving MLaaS with Tiny Clients
URI https://ieeexplore.ieee.org/document/10631031
WOSCitedRecordID wos001304430200115&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI5g4sBpPIZ4KweugTZtk5ZrYQJpbJU60G5TXpUqoW7aC-3fY3cd48KBW5UqiuTEduz480fInbTW6MIo5qQ0LIwjzpRRMQsVHB8BLj2sWRQ-erLfj0ejJGvA6jUWxjlXF5-5e_ys3_LtxCwxVQYaLpAWC4KdfSnlBqy1q-eIRdBAdHwveXhNn9JcoDeEIJBji2wfUe2_KFRqD9Jt_3PtI9LZYfFo9uNljsmeq05Ie0vGQBvdPCWLPBsMH2le94NdzmASGFlML1FVWTpYYd5uSodfrqafonBXpZvOxWDuaFZOEZeOP8oKlitXyqwZlmegKYHRt55SOcWkLR2W1Zqmn4ijnHfIe_d5mL6whlKBlb4UC5YYHhaJDYIgAsUtlNWJVsK33PkWgmEjQSE9y73CK-Aq6BklwATIyHmedbGOkuCMtKpJ5c4J1RpiNaFCbSQPnbWx5iaMPMWFjSOXqAvSQSmOp5uuGeOtAC__GL8ih7hRmDflwTVpgbjcDTkwq0U5n93We_0NjrirsQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI7QQILTeAzxJgeuhTZN05ZrYdpEt1VaQbtNaZJKlVA37YX277G7jnHhwK1KFUVyYjt2_Pkj5MHXWmW5kpbxfWXxwGOWVDKwuITjI8Cl84pF4SP2-_1gNAqTGqxeYWGMMVXxmXnEz-otX0_UElNloOECabEg2Nn3OGfOBq61q-gIhFuDdBw7fOpGL9FQoD-EMJBhk2wHce2_SFQqH9Ju_nP1Y9LaofFo8uNnTsieKU9Jc0vHQGvtPCOLYTJIn-mw6gi7nMEkMLOYYKKy1HSwwszdlKZfpiKgonBbpZvexWDwaFJMEZmOP4oSlitWUq0tLNBAYwKjvVjKIcW0LU2Lck2jT0RSzlvkvf2aRh2rJlWwCscXCytUjOehdl3XA9XNpc7CTApHM-NoCIeVDyppa2bndg6XQVtJAUbA94xtaxNkXuiek0Y5Kc0FoVkG0ZqQPFM-40brIGOKe7ZkQgeeCeUlaaEUx9NN34zxVoBXf4zfk8NO2ovHcbf_dk2OcNMwi8rcG9IA0ZlbcqBWi2I-u6v2_Ruo4a74
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%3Abook&rft.genre=proceeding&rft.title=Proceedings+of+the+International+Conference+on+Distributed+Computing+Systems&rft.atitle=SPOT%3A+Structure+Patching+and+Overlap+Tweaking+for+Effective+Pipelining+in+Privacy-Preserving+MLaaS+with+Tiny+Clients&rft.au=Xu%2C+Xiangrui&rft.au=Zhang%2C+Qiao&rft.au=Ning%2C+Rui&rft.au=Xin%2C+Chunsheng&rft.date=2024-07-23&rft.pub=IEEE&rft.eissn=2575-8411&rft.spage=1318&rft.epage=1329&rft_id=info:doi/10.1109%2FICDCS60910.2024.00124&rft.externalDocID=10631031