<?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-00324858</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="2026-05-15T14:24:39+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">WebGuard: Web-Based Adult Content Detection and Filtering System</title>
            <author role="aut">
              <persName>
                <forename type="first">Mohamed</forename>
                <surname>Hammami</surname>
              </persName>
              <idno type="halauthorid">247569-0</idno>
              <affiliation ref="#struct-2003"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Youssef</forename>
                <surname>Chahir</surname>
              </persName>
              <email type="md5">4d94867671c86bc25e15b24c45a02625</email>
              <email type="domain">unicaen.fr</email>
              <idno type="idhal" notation="string">youssef-chahir</idno>
              <idno type="idhal" notation="numeric">20234</idno>
              <idno type="halauthorid" notation="string">26062-20234</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-1417-5317</idno>
              <idno type="IDREF">https://www.idref.fr/15333293X</idno>
              <affiliation ref="#struct-406734"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Liming</forename>
                <surname>Chen</surname>
              </persName>
              <email type="md5">0423f26101c540dbb848c33d738f388d</email>
              <email type="domain">ec-lyon.fr</email>
              <idno type="idhal" notation="string">liming-chen</idno>
              <idno type="idhal" notation="numeric">7562</idno>
              <idno type="halauthorid" notation="string">18211-7562</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?hl=fr&amp;user=VOPW5YYAAAAJ</idno>
              <idno type="IDREF">https://www.idref.fr/067400175</idno>
              <affiliation ref="#struct-2003"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Dodola</forename>
                <surname>Greyc</surname>
              </persName>
              <email type="md5">4b085ea45eeab8984354526e6cefcbd2</email>
              <email type="domain">greyc.fr.invalid</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2008-09-25 16:40:59</date>
              <date type="whenModified">2025-09-03 10:01:42</date>
              <date type="whenReleased">2008-09-25 16:56:45</date>
              <date type="whenProduced">2003</date>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="131744">
                <persName>
                  <forename>Dodola</forename>
                  <surname>Greyc</surname>
                </persName>
                <email type="md5">4b085ea45eeab8984354526e6cefcbd2</email>
                <email type="domain">greyc.fr.invalid</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-00324858</idno>
            <idno type="halUri">https://hal.science/hal-00324858</idno>
            <idno type="halBibtex">hammami:hal-00324858</idno>
            <idno type="halRefHtml">&lt;i&gt;IEEE/WIC International Conference on Web Intelligence (WI'03)&lt;/i&gt;, 2003, Halifax, Canada. pp.574-578, &lt;a target="_blank" href="https://dx.doi.org/10.1109/WI.2003.1241271"&gt;&amp;#x27E8;10.1109/WI.2003.1241271&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">IEEE/WIC International Conference on Web Intelligence (WI'03), 2003, Halifax, Canada. pp.574-578, &amp;#x27E8;10.1109/WI.2003.1241271&amp;#x27E9;</idno>
            <availability status="restricted"/>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="UNIV-LYON1">Université Claude Bernard - Lyon I</idno>
            <idno type="stamp" n="UNIV-LYON2">Université Lumière Lyon 2</idno>
            <idno type="stamp" n="INSA-LYON">Institut National des Sciences Appliquées de Lyon</idno>
            <idno type="stamp" n="EC-LYON">Ecole Centrale de Lyon</idno>
            <idno type="stamp" n="ENSI-CAEN">Ecole Nationale Supérieure d'Ingénieurs de Caen</idno>
            <idno type="stamp" n="LIRIS" corresp="UNIV-LYON1">Laboratoire d'InfoRmatique en Image et Systèmes d'information</idno>
            <idno type="stamp" n="GREYC">Groupe de Recherche en Informatique, Image, Automatique et Instrumentation de Caen (GREYC)</idno>
            <idno type="stamp" n="GREYC-IMAGE" corresp="GREYC">GREYC image</idno>
            <idno type="stamp" n="COMUE-NORMANDIE">Normandie Université</idno>
            <idno type="stamp" n="ENSICAEN">École Nationale Supérieure d’Ingénieurs de Caen</idno>
            <idno type="stamp" n="UNICAEN">Université de Caen Normandie</idno>
            <idno type="stamp" n="INSA-GROUPE">Groupe INSA</idno>
            <idno type="stamp" n="UDL">UDL</idno>
            <idno type="stamp" n="UNIV-LYON">Université de Lyon</idno>
            <idno type="stamp" n="EC_LYON_STRICT">Centrale Lyon - périmètre strict</idno>
            <idno type="stamp" n="HAL-LYON-2-NOUVELLE-VERSION">Nouvelle version portail </idno>
          </seriesStmt>
          <notesStmt>
            <note type="commentary">@inproceedings{CI-CHAHIR-2003, author = {Hammami, M. and Chahir, Y. and Chen, L.}, title = {WebGuard: Web-Based Adult Content Detection and Filtering System}, booktitle = {IEEE/WIC International Conference on Web Intelligence (WI'03)}, pages = {574-578}, year = {2003}, address = {Halifax, Canada}, month = {October} }</note>
            <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">WebGuard: Web-Based Adult Content Detection and Filtering System</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Mohamed</forename>
                    <surname>Hammami</surname>
                  </persName>
                  <idno type="halauthorid">247569-0</idno>
                  <affiliation ref="#struct-2003"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Youssef</forename>
                    <surname>Chahir</surname>
                  </persName>
                  <email type="md5">4d94867671c86bc25e15b24c45a02625</email>
                  <email type="domain">unicaen.fr</email>
                  <idno type="idhal" notation="string">youssef-chahir</idno>
                  <idno type="idhal" notation="numeric">20234</idno>
                  <idno type="halauthorid" notation="string">26062-20234</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-1417-5317</idno>
                  <idno type="IDREF">https://www.idref.fr/15333293X</idno>
                  <affiliation ref="#struct-406734"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Liming</forename>
                    <surname>Chen</surname>
                  </persName>
                  <email type="md5">0423f26101c540dbb848c33d738f388d</email>
                  <email type="domain">ec-lyon.fr</email>
                  <idno type="idhal" notation="string">liming-chen</idno>
                  <idno type="idhal" notation="numeric">7562</idno>
                  <idno type="halauthorid" notation="string">18211-7562</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?hl=fr&amp;user=VOPW5YYAAAAJ</idno>
                  <idno type="IDREF">https://www.idref.fr/067400175</idno>
                  <affiliation ref="#struct-2003"/>
                </author>
              </analytic>
              <monogr>
                <meeting>
                  <title>IEEE/WIC International Conference on Web Intelligence (WI'03)</title>
                  <date type="start">2003</date>
                  <settlement>Halifax</settlement>
                  <country key="CA">Canada</country>
                </meeting>
                <imprint>
                  <biblScope unit="pp">574-578</biblScope>
                  <date type="datePub">2003</date>
                </imprint>
              </monogr>
              <idno type="doi">10.1109/WI.2003.1241271</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <classCode scheme="halDomain" n="scco.comp">Cognitive science/Computer science</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>We describe a Web filtering system "WebGuard", which aims to automatically detect and filter adult content on the Web. WebGuard uses Web crawler to extract relevant data from the Web, combines the textual content, the image content, and the URL name of a Web page to construct its feature vector. WebGuard uses data mining techniques to classify URLs into two classes: suspect URLs and normal URLs. The suspect URLs are stored in a database, which is constantly and automatically updated in order to reflect the highly dynamic evolution of the Web. When working, WebGuard simply captures a user's URL, matches it with the suspect URLs stored in the database and takes an appropriate action - filtering or blocking - according to the result of the analysis. Our preliminary results show that it can detect and filter adult content effectively.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="laboratory" xml:id="struct-2003" status="VALID">
          <idno type="IdRef">149705271</idno>
          <idno type="ISNI">0000000122577669</idno>
          <idno type="RNSR">200511875R</idno>
          <idno type="ROR">https://ror.org/04dv4he91</idno>
          <orgName>Laboratoire d'InfoRmatique en Image et Systèmes d'information</orgName>
          <orgName type="acronym">LIRIS</orgName>
          <date type="start">2003-01-01</date>
          <desc>
            <address>
              <addrLine>Bâtiment Blaise Pascal - 20, avenue Albert Einstein - 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://liris.cnrs.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-33804" type="direct"/>
            <relation active="#struct-126765" type="direct"/>
            <relation active="#struct-301088" type="indirect"/>
            <relation active="#struct-194495" type="direct"/>
            <relation active="#struct-219748" type="direct"/>
            <relation active="#struct-301232" type="indirect"/>
            <relation name="UMR5205" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="researchteam" xml:id="struct-406734" status="VALID">
          <orgName>Equipe Image - Laboratoire GREYC - UMR6072</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
          <listRelation>
            <relation active="#struct-150" type="direct"/>
            <relation active="#struct-7127" type="indirect"/>
            <relation active="#struct-455934" type="indirect"/>
            <relation active="#struct-246955" type="indirect"/>
            <relation name="UMR6072" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-33804" status="VALID">
          <idno type="IdRef">02640334X</idno>
          <idno type="ISNI">0000 0001 2188 0906</idno>
          <idno type="ROR">https://ror.org/03rth4p18</idno>
          <idno type="Wikidata">Q4041</idno>
          <orgName>Université Lumière - Lyon 2</orgName>
          <orgName type="acronym">UL2</orgName>
          <desc>
            <address>
              <addrLine>86, rue Pasteur - 69007 Lyon</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon2.fr</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-126765" status="VALID">
          <idno type="ROR">https://ror.org/05s6rge65</idno>
          <orgName>École Centrale de Lyon</orgName>
          <orgName type="acronym">ECL</orgName>
          <desc>
            <address>
              <addrLine>36 avenue Guy de Collongue - 69134 Ecully cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ec-lyon.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301088" status="VALID">
          <idno type="ROR">https://ror.org/01rk35k63</idno>
          <orgName>Université de Lyon</orgName>
          <desc>
            <address>
              <addrLine>92 rue Pasteur - CS 30122, 69361 Lyon Cedex 07</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.universite-lyon.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-194495" status="VALID">
          <idno type="IdRef">026402823</idno>
          <idno type="ISNI">0000000121686185</idno>
          <idno type="ROR">https://ror.org/029brtt94</idno>
          <orgName>Université Claude Bernard Lyon 1</orgName>
          <orgName type="acronym">UCBL</orgName>
          <desc>
            <address>
              <addrLine>43, boulevard du 11 novembre 1918, 69622 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.univ-lyon1.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-219748" status="VALID">
          <idno type="IdRef">052444724</idno>
          <idno type="ISNI">0000 0001 2292 0228</idno>
          <orgName>Institut National des Sciences Appliquées de Lyon</orgName>
          <orgName type="acronym">INSA Lyon</orgName>
          <date type="start">1957-03-18</date>
          <desc>
            <address>
              <addrLine>20 Avenue Albert Einstein, 69621 Villeurbanne cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.insa-lyon.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-301088" type="direct"/>
            <relation active="#struct-301232" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-301232" status="VALID">
          <idno type="IdRef">162105150</idno>
          <orgName>Institut National des Sciences Appliquées</orgName>
          <orgName type="acronym">INSA</orgName>
          <desc>
            <address>
              <country key="FR"/>
            </address>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
        <org type="laboratory" xml:id="struct-150" status="VALID">
          <idno type="IdRef">035827335</idno>
          <idno type="ISNI">0000 0000 9466 2590</idno>
          <idno type="RNSR">201722568L</idno>
          <idno type="ROR">https://ror.org/043749971</idno>
          <idno type="Wikidata">Q3117752</idno>
          <orgName>Groupe de Recherche en Informatique, Image et Instrumentation de Caen</orgName>
          <orgName type="acronym">GREYC</orgName>
          <date type="start">1995-01-01</date>
          <desc>
            <address>
              <addrLine>Boulevard du Maréchal Juin - 14050 CAEN Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.greyc.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-7127" type="direct"/>
            <relation active="#struct-455934" type="indirect"/>
            <relation active="#struct-246955" type="direct"/>
            <relation name="UMR6072" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-7127" status="VALID">
          <idno type="IdRef">026403064</idno>
          <idno type="ISNI">0000000121864076</idno>
          <idno type="ROR">https://ror.org/051kpcy16</idno>
          <orgName>Université de Caen Normandie</orgName>
          <orgName type="acronym">UNICAEN</orgName>
          <date type="start">1432-01-01</date>
          <desc>
            <address>
              <addrLine>Esplanade de la Paix - CS 14032 - 14032 CAEN Cedex 5</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.unicaen.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-455934" type="direct"/>
          </listRelation>
        </org>
        <org type="regroupinstitution" xml:id="struct-455934" status="VALID">
          <idno type="IdRef">190906332</idno>
          <idno type="ISNI">0000000417859671 </idno>
          <idno type="ROR">https://ror.org/01k40cz91</idno>
          <orgName>Normandie Université</orgName>
          <orgName type="acronym">NU</orgName>
          <date type="start">2015-01-01</date>
          <desc>
            <address>
              <addrLine>Esplanade de la Paix - CS 14032 - 14032 Caen Cedex 5</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.normandie-univ.fr/</ref>
          </desc>
        </org>
        <org type="institution" xml:id="struct-246955" status="VALID">
          <idno type="IdRef">190907991</idno>
          <idno type="ROR">https://ror.org/01fpqqe90</idno>
          <orgName>École Nationale Supérieure d'Ingénieurs de Caen</orgName>
          <orgName type="acronym">ENSICAEN</orgName>
          <desc>
            <address>
              <addrLine>6, Boulevard du Maréchal Juin CS 45053 14050 CAEN cedex 04</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.ensicaen.fr/</ref>
          </desc>
          <listRelation>
            <relation active="#struct-455934" type="direct"/>
          </listRelation>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>