his.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Integrally private model selection for decision trees
Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi. (Skövde Artificial Intelligence Lab)ORCID-id: 0000-0002-2564-0683
Högskolan i Skövde, Institutionen för informationsteknologi. Högskolan i Skövde, Forskningscentrum för Informationsteknologi. Maynooth University Hamilton Institute, Kildare, Ireland. (Skövde Artificial Intelligence Lab)ORCID-id: 0000-0002-0368-8037
2019 (engelsk)Inngår i: Computers & security (Print), ISSN 0167-4048, E-ISSN 1872-6208, Vol. 83, s. 167-181Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Privacy attacks targeting machine learning models are evolving. One of the primary goals of such attacks is to infer information about the training data used to construct the models. “Integral Privacy” focuses on machine learning and statistical models which explain how we can utilize intruder's uncertainty to provide a privacy guarantee against model comparison attacks. Through experimental results, we show how the distribution of models can be used to achieve integral privacy. Here, we observe two categories of machine learning models based on their frequency of occurrence in the model space. Then we explain the privacy implications of selecting each of them based on a new attack model and empirical results. Also, we provide recommendations for private model selection based on the accuracy and stability of the models along with the diversity of training data that can be used to generate the models. 

sted, utgiver, år, opplag, sider
Elsevier Ltd , 2019. Vol. 83, s. 167-181
Emneord [en]
Data privacy, Integral privacy, Machine learning model space, Privacy models, Privacy preserving machine learning, Decision trees, Attack model, Machine learning models, Model comparison, Model Selection, Privacy Attacks, Privacy preserving, Training data, Machine learning
HSV kategori
Forskningsprogram
Skövde Artificial Intelligence Lab (SAIL)
Identifikatorer
URN: urn:nbn:se:his:diva-16682DOI: 10.1016/j.cose.2019.01.006ISI: 000465367100013Scopus ID: 2-s2.0-85062062700OAI: oai:DiVA.org:his-16682DiVA, id: diva2:1294621
Tilgjengelig fra: 2019-03-08 Laget: 2019-03-08 Sist oppdatert: 2019-07-10bibliografisk kontrollert

Open Access i DiVA

fulltext(2775 kB)94 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 2775 kBChecksum SHA-512
470d260e414699fc4350e143639211ed36ad9526dbd76c0fde83c97e3c748499adaaa5e7b6c3239064dc19accc1d2eb03883779e9d24f03fd780389844a3b8b8
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Senavirathne, NavodaTorra, Vicenç

Søk i DiVA

Av forfatter/redaktør
Senavirathne, NavodaTorra, Vicenç
Av organisasjonen
I samme tidsskrift
Computers & security (Print)

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 94 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 321 treff
RefereraExporteraLink to record
Permanent link

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