View in EDS

Evaluation of Open-Source Tools for Differential Privacy

Saved in:
Bibliographic Details
Title: Evaluation of Open-Source Tools for Differential Privacy
Authors: Zhang, Shiliang, 1988, Hagermalm, Anton, Slavnic, Sanjin, Schiller, Elad, 1974, Almgren, Magnus, 1972
Source: AutoSPADA (Automotive Stream Processing and Distributed Analytics) OODIDA Phase 2 Sensors. 23(14)
Subject Terms: open-source tools, differential privacy, evaluation
Description: Differential privacy (DP) defines privacy protection by promising quantified indistinguishability between individuals who consent to share their privacy-sensitive information and those who do not. DP aims to deliver this promise by including well-crafted elements of random noise in the published data, and thus there is an inherent tradeoff between the degree of privacy protection and the ability to utilize the protected data. Currently, several open-source tools have been proposed for DP provision. To the best of our knowledge, there is no comprehensive study for comparing these open-source tools with respect to their ability to balance DP's inherent tradeoff as well as the use of system resources. This work proposes an open-source evaluation framework for privacy protection solutions and offers evaluation for OpenDP Smartnoise, Google DP, PyTorch Opacus, Tensorflow Privacy, and Diffprivlib. In addition to studying their ability to balance the above tradeoff, we consider discrete and continuous attributes by quantifying their performance under different data sizes. Our results reveal several patterns that developers should have in mind when selecting tools under different application needs and criteria. This evaluation survey can be the basis for an improved selection of open-source DP tools and quicker adaptation of DP.
File Description: electronic
Access URL: https://research.chalmers.se/publication/540801
https://research.chalmers.se/publication/540801/file/540801_Fulltext.pdf
Database: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://research.chalmers.se/publication/540801#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=search&db=pmc&term=1424-8220[TA]+AND+[PG]+AND+2023[PDAT]
    Name: FREE - PubMed Central (ISSN based link)
    Category: fullText
    Text: Full Text
    Icon: https://imageserver.ebscohost.com/NetImages/iconPdf.gif
    MouseOverText: Check this PubMed for the article full text.
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=14248220&ISBN=&volume=23&issue=14&date=20230101&spage=&pages=&title=AutoSPADA (Automotive Stream Processing and Distributed Analytics) OODIDA Phase 2 Sensors&atitle=Evaluation%20of%20Open-Source%20Tools%20for%20Differential%20Privacy&aulast=Zhang%2C%20Shiliang&id=DOI:10.3390/s23146509
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Zhang%20S
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.research.chalmers.se.12f08718.d7b1.4bfe.948d.699b3216abc0
RelevancyScore: 984
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 983.779541015625
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Evaluation of Open-Source Tools for Differential Privacy
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zhang%2C+Shiliang%22">Zhang, Shiliang</searchLink>, 1988<br /><searchLink fieldCode="AR" term="%22Hagermalm%2C+Anton%22">Hagermalm, Anton</searchLink><br /><searchLink fieldCode="AR" term="%22Slavnic%2C+Sanjin%22">Slavnic, Sanjin</searchLink><br /><searchLink fieldCode="AR" term="%22Schiller%2C+Elad%22">Schiller, Elad</searchLink>, 1974<br /><searchLink fieldCode="AR" term="%22Almgren%2C+Magnus%22">Almgren, Magnus</searchLink>, 1972
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>AutoSPADA (Automotive Stream Processing and Distributed Analytics) OODIDA Phase 2 Sensors</i>. 23(14)
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22open-source+tools%22">open-source tools</searchLink><br /><searchLink fieldCode="DE" term="%22differential+privacy%22">differential privacy</searchLink><br /><searchLink fieldCode="DE" term="%22evaluation%22">evaluation</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Differential privacy (DP) defines privacy protection by promising quantified indistinguishability between individuals who consent to share their privacy-sensitive information and those who do not. DP aims to deliver this promise by including well-crafted elements of random noise in the published data, and thus there is an inherent tradeoff between the degree of privacy protection and the ability to utilize the protected data. Currently, several open-source tools have been proposed for DP provision. To the best of our knowledge, there is no comprehensive study for comparing these open-source tools with respect to their ability to balance DP's inherent tradeoff as well as the use of system resources. This work proposes an open-source evaluation framework for privacy protection solutions and offers evaluation for OpenDP Smartnoise, Google DP, PyTorch Opacus, Tensorflow Privacy, and Diffprivlib. In addition to studying their ability to balance the above tradeoff, we consider discrete and continuous attributes by quantifying their performance under different data sizes. Our results reveal several patterns that developers should have in mind when selecting tools under different application needs and criteria. This evaluation survey can be the basis for an improved selection of open-source DP tools and quicker adaptation of DP.
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/540801" linkWindow="_blank">https://research.chalmers.se/publication/540801</link><br /><link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/540801/file/540801_Fulltext.pdf" linkWindow="_blank">https://research.chalmers.se/publication/540801/file/540801_Fulltext.pdf</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.research.chalmers.se.12f08718.d7b1.4bfe.948d.699b3216abc0
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/s23146509
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: open-source tools
        Type: general
      – SubjectFull: differential privacy
        Type: general
      – SubjectFull: evaluation
        Type: general
    Titles:
      – TitleFull: Evaluation of Open-Source Tools for Differential Privacy
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zhang, Shiliang
      – PersonEntity:
          Name:
            NameFull: Hagermalm, Anton
      – PersonEntity:
          Name:
            NameFull: Slavnic, Sanjin
      – PersonEntity:
          Name:
            NameFull: Schiller, Elad
      – PersonEntity:
          Name:
            NameFull: Almgren, Magnus
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 14248220
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: CTH_SWEPUB
          Numbering:
            – Type: volume
              Value: 23
            – Type: issue
              Value: 14
          Titles:
            – TitleFull: AutoSPADA (Automotive Stream Processing and Distributed Analytics) OODIDA Phase 2 Sensors
              Type: main
ResultId 1