Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Dissecting Membership Inference Risk in Machine Learning
School of Informatics, University of Skövde, Skövde, Sweden.
Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0002-0368-8037
2022 (English)In: Cyberspace Safety and Security: 13th International Symposium, CSS 2021, Virtual Event, November 9–11, 2021, Proceedings / [ed] Weizhi Meng; Mauro Conti, Springer, 2022, p. 36-54Conference paper, Published paper (Refereed)
Abstract [en]

Membership inference attacks (MIA) have been identified as a distinct threat to privacy when sensitive personal data are used to train the machine learning (ML) models. This work is aimed at deepening our understanding with respect to the existing black-box MIAs while introducing a new label only MIA model. The proposed MIA model can successfully exploit the well generalized models challenging the conventional wisdom that states generalized models are immune to membership inference. Through systematic experimentation, we show that the proposed MIA model can outperform the existing attack models while being more resilient towards manipulations to the membership inference results caused by the selection of membership validation data.

Place, publisher, year, edition, pages
Springer, 2022. p. 36-54
Series
Lecture Notes in Computer Science (LNCS), ISSN 0302-9743, E-ISSN 1611-3349 ; 13172
Keywords [en]
Data privacy, Membership inference attack, Privacy preserving machine learning
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:umu:diva-192168DOI: 10.1007/978-3-030-94029-4_3Scopus ID: 2-s2.0-85123431800ISBN: 978-3-030-94028-7 (print)ISBN: 978-3-030-94029-4 (electronic)OAI: oai:DiVA.org:umu-192168DiVA, id: diva2:1634645
Conference
CSS 2021, 13th International Symposium on Cyberspace Safety and Security, Virtual, November 9-11, 2021
Available from: 2022-02-03 Created: 2022-02-03 Last updated: 2023-03-24Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Torra, Vicenç

Search in DiVA

By author/editor
Torra, Vicenç
By organisation
Department of Computing Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 200 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf