<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04165346</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-16T21:03:26+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Quantifying the contribution of individual records to the reidentification risk of (pseudo) anonymized datasets</title>
            <author role="aut">
              <persName>
                <forename type="first">Michel</forename>
                <surname>Béra</surname>
              </persName>
              <email type="md5">c416d47a5b8063839daff0532069e397</email>
              <email type="domain">lecnam.net</email>
              <idno type="idhal" notation="numeric">1064267</idno>
              <idno type="halauthorid" notation="string">671741-1064267</idno>
              <affiliation ref="#struct-390785"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Vasiliki</forename>
                <surname>Daskalaki</surname>
              </persName>
              <email type="md5">c928cb6822bfe23a7b826648b316e0db</email>
              <email type="domain">quantos-stat.com</email>
              <idno type="idhal" notation="numeric">1271111</idno>
              <idno type="halauthorid" notation="string">2863408-1271111</idno>
              <affiliation ref="#struct-1058908"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Gilbert</forename>
                <surname>Saporta</surname>
              </persName>
              <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
              <email type="domain">cnam.fr</email>
              <idno type="idhal" notation="string">gilbert-saporta</idno>
              <idno type="idhal" notation="numeric">180161</idno>
              <idno type="halauthorid" notation="string">4563-180161</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-3406-5887</idno>
              <idno type="IDREF">https://www.idref.fr/027122565</idno>
              <idno type="ARXIV">https://arxiv.org/a/saporta_g_1</idno>
              <affiliation ref="#struct-390785"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Kimon</forename>
                <surname>Spiliopoulos</surname>
              </persName>
              <idno type="halauthorid">485891-0</idno>
              <affiliation ref="#struct-1058908"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Konstantinos</forename>
                <surname>Spinakis</surname>
              </persName>
              <email type="md5">b7a286093e264beb9e8e64fec6d1faed</email>
              <email type="domain">epfl.ch</email>
              <idno type="idhal" notation="numeric">1271112</idno>
              <idno type="halauthorid" notation="string">2863409-1271112</idno>
              <affiliation ref="#struct-147972"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Photis</forename>
                <surname>Stavropoulos</surname>
              </persName>
              <email type="md5">f5598ee352d0adc0f0bd408e2aabedd4</email>
              <email type="domain">quantos-stat.com</email>
              <idno type="idhal" notation="numeric">1271113</idno>
              <idno type="halauthorid" notation="string">2863410-1271113</idno>
              <affiliation ref="#struct-1058908"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Gilbert</forename>
                <surname>Saporta</surname>
              </persName>
              <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
              <email type="domain">cnam.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-07-18 19:40:13</date>
              <date type="whenModified">2025-07-09 15:06:18</date>
              <date type="whenReleased">2023-07-24 14:42:00</date>
              <date type="whenProduced">2023-07-16</date>
              <date type="whenEndEmbargoed">2023-07-18</date>
              <ref type="file" target="https://cnam.hal.science/hal-04165346v1/document">
                <date notBefore="2023-07-18"/>
              </ref>
              <ref type="file" subtype="greenPublisher" n="1" target="https://cnam.hal.science/hal-04165346v1/file/ottawa-2023_3a7332d6240cfd6fb54c54f8f7782d29.pdf" id="file-4165346-3627215">
                <date notBefore="2023-07-18"/>
              </ref>
              <ref type="annex" n="0" target="https://cnam.hal.science/hal-04165346v1/file/Ottawa_Z90%20V1.0%2013jul23.pdf" id="file-4165346-3627216">
                <date notBefore="2023-07-18"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="167713">
                <persName>
                  <forename>Gilbert</forename>
                  <surname>Saporta</surname>
                </persName>
                <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
                <email type="domain">cnam.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04165346</idno>
            <idno type="halUri">https://cnam.hal.science/hal-04165346</idno>
            <idno type="halBibtex">bera:hal-04165346</idno>
            <idno type="halRefHtml">&lt;i&gt;64th ISI World Statistics Congress&lt;/i&gt;, International Statistical Institute, Jul 2023, Ottawa (Ontario), Canada</idno>
            <idno type="halRef">64th ISI World Statistics Congress, International Statistical Institute, Jul 2023, Ottawa (Ontario), Canada</idno>
            <availability status="restricted">
              <licence target="https://about.hal.science/hal-authorisation-v1/">HAL Authorization<ref corresp="#file-4165346-3627215"/><ref corresp="#file-4165346-3627216"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNAM">Conservatoire National des Arts et Métiers</idno>
            <idno type="stamp" n="CEDRIC-CNAM" corresp="CNAM">Centre d'études et de recherche en informatique et communications </idno>
            <idno type="stamp" n="HESAM-CNAM" corresp="HESAM">Conservatoire National des Arts et Métiers - Hesam</idno>
            <idno type="stamp" n="HESAM">Hesam</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="invited" n="0">No</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
            <note type="proceedings" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Quantifying the contribution of individual records to the reidentification risk of (pseudo) anonymized datasets</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Michel</forename>
                    <surname>Béra</surname>
                  </persName>
                  <email type="md5">c416d47a5b8063839daff0532069e397</email>
                  <email type="domain">lecnam.net</email>
                  <idno type="idhal" notation="numeric">1064267</idno>
                  <idno type="halauthorid" notation="string">671741-1064267</idno>
                  <affiliation ref="#struct-390785"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Vasiliki</forename>
                    <surname>Daskalaki</surname>
                  </persName>
                  <email type="md5">c928cb6822bfe23a7b826648b316e0db</email>
                  <email type="domain">quantos-stat.com</email>
                  <idno type="idhal" notation="numeric">1271111</idno>
                  <idno type="halauthorid" notation="string">2863408-1271111</idno>
                  <affiliation ref="#struct-1058908"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Gilbert</forename>
                    <surname>Saporta</surname>
                  </persName>
                  <email type="md5">6298c57098dc5d21247fd35757d2103d</email>
                  <email type="domain">cnam.fr</email>
                  <idno type="idhal" notation="string">gilbert-saporta</idno>
                  <idno type="idhal" notation="numeric">180161</idno>
                  <idno type="halauthorid" notation="string">4563-180161</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-3406-5887</idno>
                  <idno type="IDREF">https://www.idref.fr/027122565</idno>
                  <idno type="ARXIV">https://arxiv.org/a/saporta_g_1</idno>
                  <affiliation ref="#struct-390785"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Kimon</forename>
                    <surname>Spiliopoulos</surname>
                  </persName>
                  <idno type="halauthorid">485891-0</idno>
                  <affiliation ref="#struct-1058908"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Konstantinos</forename>
                    <surname>Spinakis</surname>
                  </persName>
                  <email type="md5">b7a286093e264beb9e8e64fec6d1faed</email>
                  <email type="domain">epfl.ch</email>
                  <idno type="idhal" notation="numeric">1271112</idno>
                  <idno type="halauthorid" notation="string">2863409-1271112</idno>
                  <affiliation ref="#struct-147972"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Photis</forename>
                    <surname>Stavropoulos</surname>
                  </persName>
                  <email type="md5">f5598ee352d0adc0f0bd408e2aabedd4</email>
                  <email type="domain">quantos-stat.com</email>
                  <idno type="idhal" notation="numeric">1271113</idno>
                  <idno type="halauthorid" notation="string">2863410-1271113</idno>
                  <affiliation ref="#struct-1058908"/>
                </author>
              </analytic>
              <monogr>
                <title level="m">Proceedings of the 64th ISI World Statistics Congress</title>
                <meeting>
                  <title>64th ISI World Statistics Congress</title>
                  <date type="start">2023-07-16</date>
                  <date type="end">2023-07-20</date>
                  <settlement>Ottawa (Ontario)</settlement>
                  <country key="CA">Canada</country>
                </meeting>
                <respStmt>
                  <resp>conferenceOrganizer</resp>
                  <name>International Statistical Institute</name>
                </respStmt>
                <imprint/>
              </monogr>
              <ref type="publisher">https://www.isi2023.org/</ref>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Anonymization</term>
                <term xml:lang="en">extreme-value theory</term>
                <term xml:lang="en">privacy</term>
                <term xml:lang="en">pseudonymization</term>
                <term xml:lang="en">reidentification</term>
                <term xml:lang="en">risk</term>
              </keywords>
              <classCode scheme="halDomain" n="stat">Statistics [stat]</classCode>
              <classCode scheme="halDomain" n="info">Computer Science [cs]</classCode>
              <classCode scheme="halTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halOldTypology" n="COMM">Conference papers</classCode>
              <classCode scheme="halTreeTypology" n="COMM">Conference papers</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The reidentification of individuals or business establishments in (pseudo)anonymized microdata may expose sensitive data and will lead to fines and reputational damage for the data's custodians. The QaR method (AFNOR, 2020) proposes a measure of the reidentification risk of a dataset, and a statistical technique, based on extreme-value theory, to estimate it. This risk has great value. It is a gauge of the effectiveness of whatever disclosure control the custodians apply to the data; it could be reported to regulatory authorities to demonstrate the custodians' level of care for the data subjects' privacy; it can be used to calculate an insurance premium against unauthorized disclosure or the amount of money that custodians need in their balance sheet to cover potential financial damages due to such disclosure. The present paper deals with a particular aspect of the methodology: the quantification of the contribution of each record to the dataset's risk. It discusses its importance and its large computational demands in very large datasets, and proposes metrics that are faster to compute and could serve as proxies of record contribution. The results for some of these proxies are promises but more investigation is needed.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-390785" status="VALID">
          <orgName>CEDRIC. Méthodes statistiques de data-mining et apprentissage</orgName>
          <orgName type="acronym">CEDRIC - MSDMA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-16574" type="direct"/>
            <relation name="EA4629" active="#struct-179741" type="indirect"/>
            <relation name="EA4629" active="#struct-300351" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-1058908" status="INCOMING">
          <orgName>Quantos</orgName>
          <desc>
            <address>
              <country key="GR"/>
            </address>
            <ref type="url">https://quantos-stat.com/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-147972" status="VALID">
          <orgName>CMCS-EPFL</orgName>
          <orgName type="acronym">CMCS-EPFL</orgName>
          <desc>
            <address>
              <country key="CH"/>
            </address>
            <ref type="url">http://cmcs.epfl.ch/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-302851" type="direct"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-16574" status="VALID">
          <idno type="IdRef">155463381</idno>
          <idno type="RNSR">201119480F</idno>
          <idno type="ROR">https://ror.org/044j5mm75</idno>
          <orgName>Centre d'études et de recherche en informatique et communications</orgName>
          <orgName type="acronym">CEDRIC</orgName>
          <desc>
            <address>
              <addrLine>292 rue Saint-Martin 75141 PARIS Cedex 03Case courrier 2D4P30</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://cedric.cnam.fr/</ref>
          </desc>
          <listRelation>
            <relation name="EA4629" active="#struct-179741" type="direct"/>
            <relation name="EA4629" active="#struct-300351" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-179741" status="VALID">
          <orgName>Ecole Nationale Supérieure d'Informatique pour l'Industrie et l'Entreprise</orgName>
          <orgName type="acronym">ENSIIE</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ensiie.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300351" status="VALID">
          <idno type="IdRef">027404978</idno>
          <idno type="ISNI">0000000121690459</idno>
          <idno type="ROR">https://ror.org/0175hh227</idno>
          <orgName>Conservatoire National des Arts et Métiers [Cnam]</orgName>
          <orgName type="acronym">Cnam</orgName>
          <desc>
            <address>
              <addrLine>292 Rue Saint-Martin, 75003 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.cnam.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-302851" status="VALID">
          <idno type="IdRef">029644631</idno>
          <idno type="ROR">https://ror.org/02s376052</idno>
          <orgName>Ecole Polytechnique Fédérale de Lausanne</orgName>
          <orgName type="acronym">EPFL</orgName>
          <desc>
            <address>
              <addrLine>CH-1015 Lausanne, Switzerland</addrLine>
              <country key="CH"/>
            </address>
            <ref type="url">https://www.epfl.ch</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>