Umeå universitets logga

umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Empirical evaluation of synthetic data created by generative models via attribute inference attack
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.ORCID-id: 0000-0002-0368-8037
2024 (Engelska)Ingår i: Privacy and identity management: sharing in a digital world / [ed] Felix Bieker; Silvia de Conca; Nils Gruschka; Meiko Jensen; Ina Schiering, Springer, 2024, s. 282-291Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

The disclosure risk of synthetic/artificial data is still being determined. Studies show that synthetic data generation techniques generate similar data to the original data and sometimes even the exact original data. Therefore, publishing synthetic datasets can endanger the privacy of users. In our work, we study the synthetic data generated from different synthetic data generation techniques, including the most recent diffusion models. We perform a disclosure risk assessment of synthetic datasets via an attribute inference attack, in which an attacker has access to a subset of publicly available features and at least one synthesized dataset, and the aim is to infer the sensitive features unknown to the attacker. We also compute the predictive accuracy and F1 score of the random forest classifier trained on several synthetic datasets. For sensitive categorical features, we show that Attribute Inference Attack is not highly feasible or successful. In contrast, for continuous attributes, we can have an approximate inference. This holds true for the synthetic datasets derived from Diffusion models, GANs, and DPGANs, which shows that we can only have approximated Attribute Inference, not the exact Attribute Inference.

Ort, förlag, år, upplaga, sidor
Springer, 2024. s. 282-291
Serie
IFIP Advances in Information and Communication Technology (IFIPAICT), ISSN 1868-4238, E-ISSN 1868-422X ; 695
Nyckelord [en]
Attribute Inference Attack, Differentially Private Generative Adversarial Networks, Diffusion Models, Generative Adversarial Networks, Privacy
Nationell ämneskategori
Datavetenskap (datalogi) Datorsystem
Identifikatorer
URN: urn:nbn:se:umu:diva-224381DOI: 10.1007/978-3-031-57978-3_18Scopus ID: 2-s2.0-85192354341ISBN: 9783031579776 (tryckt)ISBN: 9783031579783 (digital)OAI: oai:DiVA.org:umu-224381DiVA, id: diva2:1860712
Konferens
18th IFIP WG 9.2, 9.6/11.7, 11.6/SIG 9.2.2 International Summer School on Privacy and Identity Management, Privacy and Identity 2023. Oslo, Norway, August 8–11, 2023
Forskningsfinansiär
Wallenberg AI, Autonomous Systems and Software Program (WASP)Tillgänglig från: 2024-05-24 Skapad: 2024-05-24 Senast uppdaterad: 2024-05-24Bibliografiskt granskad

Open Access i DiVA

fulltext(392 kB)24 nedladdningar
Filinformation
Filnamn FULLTEXT01.pdfFilstorlek 392 kBChecksumma SHA-512
160603fc6eb97f2cf59215553dbcfec0983b64e3378b71aacb251ecef2d78594e4648f71e7d5a7904d921bf68dbca1c1d37ebf1a315fa21001348fe5c99a1db2
Typ fulltextMimetyp application/pdf

Övriga länkar

Förlagets fulltextScopus

Person

Kwatra, SaloniTorra, Vicenç

Sök vidare i DiVA

Av författaren/redaktören
Kwatra, SaloniTorra, Vicenç
Av organisationen
Institutionen för datavetenskap
Datavetenskap (datalogi)Datorsystem

Sök vidare utanför DiVA

GoogleGoogle Scholar
Totalt: 24 nedladdningar
Antalet nedladdningar är summan av nedladdningar för alla fulltexter. Det kan inkludera t.ex tidigare versioner som nu inte längre är tillgängliga.

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 139 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf