Zobrazit v EDS

Privacy-Preserving Representations are not Enough: Recovering Scene Content from Camera Poses

Uloženo v:
Podrobná bibliografie
Název: Privacy-Preserving Representations are not Enough: Recovering Scene Content from Camera Poses
Autoři: Chelani, Kunal, 1992, Sattler, Torsten, Kahl, Fredrik, 1972, Kukelova, Zuzana
Zdroj: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, Canada Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2023-June:13132-13141
Témata: 3D from multi-view and sensors
Popis: Visual localization is the task of estimating the camera pose from which a given image was taken and is central to several 3D computer vision applications. With the rapid growth in the popularity of AR/VR/MR devices and cloudbased applications, privacy issues are becoming a very important aspect of the localization process. Existing work on privacy-preserving localization aims to defend against an attacker who has access to a cloud-based service. In this paper, we show that an attacker can learn about details of a scene without any access by simply querying a localization service. The attack is based on the observation that modern visual localization algorithms are robust to variations in appearance and geometry. While this is in general a desired property, it also leads to algorithms localizing objects that are similar enough to those present in a scene. An attacker can thus query a server with a large enough set of images of objects, e.g., obtained from the Internet, and some of them will be localized. The attacker can thus learn about object placements from the camera poses returned by the service (which is the minimal information returned by such a service). In this paper, we develop a proof-of-concept version of this attack and demonstrate its practical feasibility. The attack does not place any requirements on the localization algorithm used, and thus also applies to privacy-preserving representations. Current work on privacy-preserving representations alone is thus insufficient.
Přístupová URL adresa: https://research.chalmers.se/publication/537969
Databáze: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=10636919&ISBN=&volume=2023-June&issue=&date=20230101&spage=13132&pages=13132-13141&title=2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, Canada Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition&atitle=Privacy-Preserving%20Representations%20are%20not%20Enough%3A%20Recovering%20Scene%20Content%20from%20Camera%20Poses&aulast=Chelani%2C%20Kunal&id=DOI:10.1109/CVPR52729.2023.01262
    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=Chelani%20K
    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.c993931c.0992.4493.8fae.2ac370dddca8
RelevancyScore: 856
AccessLevel: 6
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 855.779541015625
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Privacy-Preserving Representations are not Enough: Recovering Scene Content from Camera Poses
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Chelani%2C+Kunal%22">Chelani, Kunal</searchLink>, 1992<br /><searchLink fieldCode="AR" term="%22Sattler%2C+Torsten%22">Sattler, Torsten</searchLink><br /><searchLink fieldCode="AR" term="%22Kahl%2C+Fredrik%22">Kahl, Fredrik</searchLink>, 1972<br /><searchLink fieldCode="AR" term="%22Kukelova%2C+Zuzana%22">Kukelova, Zuzana</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, Canada Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition</i>. 2023-June:13132-13141
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%223D+from+multi-view+and+sensors%22">3D from multi-view and sensors</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Visual localization is the task of estimating the camera pose from which a given image was taken and is central to several 3D computer vision applications. With the rapid growth in the popularity of AR/VR/MR devices and cloudbased applications, privacy issues are becoming a very important aspect of the localization process. Existing work on privacy-preserving localization aims to defend against an attacker who has access to a cloud-based service. In this paper, we show that an attacker can learn about details of a scene without any access by simply querying a localization service. The attack is based on the observation that modern visual localization algorithms are robust to variations in appearance and geometry. While this is in general a desired property, it also leads to algorithms localizing objects that are similar enough to those present in a scene. An attacker can thus query a server with a large enough set of images of objects, e.g., obtained from the Internet, and some of them will be localized. The attacker can thus learn about object placements from the camera poses returned by the service (which is the minimal information returned by such a service). In this paper, we develop a proof-of-concept version of this attack and demonstrate its practical feasibility. The attack does not place any requirements on the localization algorithm used, and thus also applies to privacy-preserving representations. Current work on privacy-preserving representations alone is thus insufficient.
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/537969" linkWindow="_blank">https://research.chalmers.se/publication/537969</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.c993931c.0992.4493.8fae.2ac370dddca8
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/CVPR52729.2023.01262
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 13132
    Subjects:
      – SubjectFull: 3D from multi-view and sensors
        Type: general
    Titles:
      – TitleFull: Privacy-Preserving Representations are not Enough: Recovering Scene Content from Camera Poses
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Chelani, Kunal
      – PersonEntity:
          Name:
            NameFull: Sattler, Torsten
      – PersonEntity:
          Name:
            NameFull: Kahl, Fredrik
      – PersonEntity:
          Name:
            NameFull: Kukelova, Zuzana
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 10636919
            – Type: issn-locals
              Value: CTH_SWEPUB
          Numbering:
            – Type: volume
              Value: 2023-June
          Titles:
            – TitleFull: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, Canada Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
              Type: main
ResultId 1