1 Ocak 2017 Dergi makalesi Açık Erişim

Gursoy, Mehmet Emre; Inan, Ali; Nergiz, Mehmet Ercan; Saygin, Yucel

MARC21 XML

<?xml version='1.0' encoding='UTF-8'?>
<record xmlns="http://www.loc.gov/MARC21/slim">
  <leader>00000nam##2200000uu#4500</leader>
  <datafield tag="909" ind1="C" ind2="4">
    <subfield code="n">5</subfield>
    <subfield code="c">1544-1575</subfield>
    <subfield code="v">31</subfield>
    <subfield code="p">DATA MINING AND KNOWLEDGE DISCOVERY</subfield>
  </datafield>
  <controlfield tag="005">20210315223940.0</controlfield>
  <datafield tag="909" ind1="C" ind2="O">
    <subfield code="o">oai:zenodo.org:50169</subfield>
    <subfield code="p">user-tubitak-destekli-proje-yayinlari</subfield>
  </datafield>
  <datafield tag="100" ind1=" " ind2=" ">
    <subfield code="u">Georgia Inst Technol, Coll Comp, Atlanta, GA 30332 USA</subfield>
    <subfield code="a">Gursoy, Mehmet Emre</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">Instance-based learning, and the k-nearest neighbors algorithm (k-NN) in particular, provide simple yet effective classification algorithms for data mining. Classifiers are often executed on sensitive information such as medical or personal data. Differential privacy has recently emerged as the accepted standard for privacy protection in sensitive data. However, straightforward applications of differential privacy to k-NN classification yield rather inaccurate results. Motivated by this, we develop algorithms to increase the accuracy of private instance-based classification. We first describe the radius neighbors classifier (r-N) and show that its accuracy under differential privacy can be greatly improved by a non-trivial sensitivity analysis. Then, for k-NN classification, we build algorithms that convert k-NN classifiers to r-N classifiers. We experimentally evaluate the accuracy of both classifiers using various datasets. Experiments show that our proposed classifiers significantly outperform baseline private classifiers (i.e., straightforward applications of differential privacy) and executing the classifiers on a dataset published using differential privacy. In addition, the accuracy of our proposed k-NN classifiers are at least comparable to, and in many cases better than, the other differentially private machine learning techniques.</subfield>
  </datafield>
  <datafield tag="542" ind1=" " ind2=" ">
    <subfield code="l">open</subfield>
  </datafield>
  <datafield tag="650" ind1="1" ind2="7">
    <subfield code="2">opendefinition.org</subfield>
    <subfield code="a">cc-by</subfield>
  </datafield>
  <datafield tag="540" ind1=" " ind2=" ">
    <subfield code="u">http://www.opendefinition.org/licenses/cc-by</subfield>
    <subfield code="a">Creative Commons Attribution</subfield>
  </datafield>
  <controlfield tag="001">50169</controlfield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">publication</subfield>
    <subfield code="b">article</subfield>
  </datafield>
  <datafield tag="245" ind1=" " ind2=" ">
    <subfield code="a">Differentially private nearest neighbor classification</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="c">2017-01-01</subfield>
  </datafield>
  <datafield tag="980" ind1=" " ind2=" ">
    <subfield code="a">user-tubitak-destekli-proje-yayinlari</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Adana Sci &amp; Technol Univ, Comp Engn Dept, Adana, Turkey</subfield>
    <subfield code="a">Inan, Ali</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Acadsoft Res, Gaziantep, Turkey</subfield>
    <subfield code="a">Nergiz, Mehmet Ercan</subfield>
  </datafield>
  <datafield tag="700" ind1=" " ind2=" ">
    <subfield code="u">Sabanci Univ, Fac Engn &amp; Nat Sci, Istanbul, Turkey</subfield>
    <subfield code="a">Saygin, Yucel</subfield>
  </datafield>
  <datafield tag="856" ind1="4" ind2=" ">
    <subfield code="u">https://aperta.ulakbim.gov.trrecord/50169/files/bib-53f73c4b-da2d-4fe4-804d-a38652ee0d16.txt</subfield>
    <subfield code="s">164</subfield>
    <subfield code="z">md5:3a018056fa45b8f23424d9c975b81159</subfield>
  </datafield>
  <datafield tag="024" ind1=" " ind2=" ">
    <subfield code="a">10.1007/s10618-017-0532-z</subfield>
    <subfield code="2">doi</subfield>
  </datafield>
</record>