<?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-04233955</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="2026-05-15T19:49:54+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Statistical properties and privacy guarantees of an original distance-based fully synthetic data generation method</title>
            <author role="aut">
              <persName>
                <forename type="first">Rémy</forename>
                <surname>Chapelle</surname>
              </persName>
              <idno type="halauthorid">2582187-0</idno>
              <affiliation ref="#struct-1051097"/>
              <affiliation ref="#struct-37967"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Bruno</forename>
                <surname>Falissard</surname>
              </persName>
              <email type="md5">1dce8041d36ec9fa504f2d70c16343c4</email>
              <email type="domain">wanadoo.fr</email>
              <idno type="idhal" notation="numeric">946495</idno>
              <idno type="halauthorid" notation="string">158567-946495</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-2418-4954</idno>
              <idno type="IDREF">https://www.idref.fr/034648739</idno>
              <affiliation ref="#struct-1051097"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Rémy</forename>
                <surname>Chapelle</surname>
              </persName>
              <email type="md5">1b98beada31a2e9ce1bdd10800708d4e</email>
              <email type="domain">universite-paris-saclay.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2023-10-09 19:29:08</date>
              <date type="whenWritten">2023</date>
              <date type="whenModified">2025-10-16 17:24:03</date>
              <date type="whenReleased">2023-10-10 14:30:28</date>
              <date type="whenProduced">2023</date>
              <date type="whenEndEmbargoed">2023-10-09</date>
              <ref type="file" target="https://hal.science/hal-04233955v1/document">
                <date notBefore="2023-10-09"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-04233955v1/file/msr_arxiv.pdf" id="file-4233955-3693072">
                <date notBefore="2023-10-09"/>
              </ref>
              <ref type="externalLink" target="http://arxiv.org/pdf/2310.06571"/>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1461845">
                <persName>
                  <forename>Rémy</forename>
                  <surname>Chapelle</surname>
                </persName>
                <email type="md5">1b98beada31a2e9ce1bdd10800708d4e</email>
                <email type="domain">universite-paris-saclay.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04233955</idno>
            <idno type="halUri">https://hal.science/hal-04233955</idno>
            <idno type="halBibtex">chapelle:hal-04233955</idno>
            <idno type="halRefHtml">2023</idno>
            <idno type="halRef">2023</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by-nc/4.0/">CC BY-NC 4.0 - Attribution - Non-commercial use<ref corresp="#file-4233955-3693072"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="SSA">Service de Santé des Armées</idno>
            <idno type="stamp" n="APHP" corresp="INSERM">AP-HP</idno>
            <idno type="stamp" n="CESP" corresp="INSERM">Centre de recherche en Épidémiologie et Santé des Populations</idno>
            <idno type="stamp" n="UVSQ">Université de Versailles Saint-Quentin-en-Yvelines</idno>
            <idno type="stamp" n="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="UVSQ-UPSACLAY" corresp="UNIV-PARIS-SACLAY">UVSQ-UPSACLAY</idno>
            <idno type="stamp" n="UNIVERSITE-PARIS-SACLAY" corresp="UNIV-PARIS-SACLAY">Université Paris-Saclay</idno>
            <idno type="stamp" n="GS-SANTE-PUBLIQUE">Graduate School Santé publique</idno>
          </seriesStmt>
          <notesStmt/>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Statistical properties and privacy guarantees of an original distance-based fully synthetic data generation method</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Rémy</forename>
                    <surname>Chapelle</surname>
                  </persName>
                  <idno type="halauthorid">2582187-0</idno>
                  <affiliation ref="#struct-1051097"/>
                  <affiliation ref="#struct-37967"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Bruno</forename>
                    <surname>Falissard</surname>
                  </persName>
                  <email type="md5">1dce8041d36ec9fa504f2d70c16343c4</email>
                  <email type="domain">wanadoo.fr</email>
                  <idno type="idhal" notation="numeric">946495</idno>
                  <idno type="halauthorid" notation="string">158567-946495</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-2418-4954</idno>
                  <idno type="IDREF">https://www.idref.fr/034648739</idno>
                  <affiliation ref="#struct-1051097"/>
                </author>
              </analytic>
              <monogr>
                <imprint/>
              </monogr>
              <idno type="arxiv">2310.06571</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">synthetic data</term>
                <term xml:lang="en">Open Science</term>
                <term xml:lang="en">disclosure control</term>
                <term xml:lang="en">risk-utility assessment</term>
              </keywords>
              <classCode scheme="halDomain" n="stat.ot">Statistics [stat]/Other Statistics [stat.ML]</classCode>
              <classCode scheme="halTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halOldTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halTreeTypology" n="UNDEFINED.PREPRINT">Preprints, Working Papers, ... - Preprint</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>Introduction: The amount of data generated by original research is growing exponentially. Publicly releasing them is recommended to comply with the Open Science principles. However, data collected from human participants cannot be released as-is without raising privacy concerns. Fully synthetic data represent a promising answer to this challenge. This approach is explored by the French Centre de Recherche en Épidémiologie et Santé des Populations in the form of a synthetic data generation framework based on Classification and Regression Trees and an original distance-based filtering. The goal of this work was to develop a refined version of this framework and to assess its risk-utility profile with empirical and formal tools, including novel ones developed for the purpose of this evaluation.Materials and Methods: Our synthesis framework consists of four successive steps, each of which is designed to prevent specific risks of disclosure. We assessed its performance by applying two or more of these steps to a rich epidemiological dataset. Privacy and utility metrics were computed for each of the resulting synthetic datasets, which were further assessed using machine learning approaches.Results: Computed metrics showed a satisfactory level of protection against attribute disclosure attacks for each synthetic dataset, especially when the full framework was used. Membership disclosure attacks were formally prevented without significantly altering the data. Machine learning approaches showed a low risk of success for simulated singling out and linkability attacks. Distributional and inferential similarity with the original data were high with all datasets.Discussion: This work showed the technical feasibility of generating publicly releasable synthetic data using a multi-step framework. Formal and empirical tools specifically developed for this demonstration are a valuable contribution to this field. Further research should focus on the extension and validation of these tools, in an effort to specify the intrinsic qualities of alternative data synthesis methods.Conclusion: By successfully assessing the quality of data produced using a novel multi-step synthetic data generation framework, we showed the technical and conceptual soundness of the Open-CESP initiative, which seems ripe for full-scale implementation.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-1051097" status="VALID">
          <idno type="IdRef">156182254</idno>
          <idno type="ISNI">0000 0004 0638 6872 </idno>
          <idno type="RNSR">201019083D</idno>
          <idno type="ROR">https://ror.org/01ed4t417</idno>
          <orgName>Centre de recherche en épidémiologie et santé des populations</orgName>
          <orgName type="acronym">CESP</orgName>
          <date type="start">2020-01-01</date>
          <desc>
            <address>
              <addrLine>16 avenue Paul Vaillant Couturier 94807 Villejuif Cedex, France</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation name="UMR U1018" active="#struct-81173" type="direct"/>
            <relation active="#struct-300068" type="direct"/>
            <relation active="#struct-300153" type="direct"/>
            <relation active="#struct-1066727" type="indirect"/>
            <relation name="U1018" active="#struct-303623" type="direct"/>
            <relation active="#struct-419361" type="direct"/>
          </listRelation>
        </org>
        <org type="regrouplaboratory" xml:id="struct-37967" status="VALID">
          <orgName>École du Val de Grâce</orgName>
          <orgName type="acronym">EVDG</orgName>
          <desc>
            <address>
              <addrLine>1 place Alphonse Laveran - 75230 Paris cedex 05</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ecole-valdegrace.sante.defense.gouv.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-300092" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-81173" status="VALID">
          <idno type="IdRef">03082057X</idno>
          <idno type="ISNI">0000 0001 2323 0229 </idno>
          <idno type="ROR">https://ror.org/03mkjjy25</idno>
          <orgName>Université de Versailles Saint-Quentin-en-Yvelines</orgName>
          <orgName type="acronym">UVSQ</orgName>
          <date type="start">1991-07-22</date>
          <desc>
            <address>
              <addrLine>55 avenue de Paris - 78035 Versailles cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.uvsq.fr/</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-300068" status="VALID">
          <idno type="ROR">https://ror.org/00pg5jh14</idno>
          <orgName>Assistance publique - Hôpitaux de Paris (AP-HP)</orgName>
          <orgName type="acronym">AP-HP</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300153" status="VALID">
          <idno type="ROR">https://ror.org/05n7yzd13</idno>
          <orgName>Hôpital Paul Brousse</orgName>
          <desc>
            <address>
              <addrLine>12 Avenue Paul Vaillant Couturier, 94800 Villejuif</addrLine>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-1066727" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-1066727" status="VALID">
          <orgName>AP-HP. Université Paris Saclay</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.aphp.fr/groupes-hospitaliers-de-lap-hp</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-303623" status="VALID">
          <idno type="IdRef">026388278</idno>
          <idno type="ROR">https://ror.org/02vjkv261</idno>
          <orgName>Institut National de la Santé et de la Recherche Médicale</orgName>
          <orgName type="acronym">INSERM</orgName>
          <desc>
            <address>
              <addrLine>101, rue de Tolbiac, 75013 Paris</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.inserm.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-419361" status="VALID">
          <idno type="IdRef">241345251</idno>
          <idno type="ROR">https://ror.org/03xjwb503</idno>
          <orgName>Université Paris-Saclay</orgName>
          <desc>
            <address>
              <addrLine>Bâtiment Bréguet, 3 Rue Joliot Curie 2e ét, 91190 Gif-sur-Yvette</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-paris-saclay.fr/fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-300092" status="VALID">
          <orgName>Service de Santé des Armées</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.defense.gouv.fr/sante</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>