Dataset Open Access

All Your Script Are Belong to Us: Collecting and Analyzing JavaScript Code from 10K Sites for 9 Months

Dimitris Mitropoulos; Panos Louridas; Vitalis Salis; Diomidis Spinellis


DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:cnt="http://www.w3.org/2011/content#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.2593266">
    <rdf:type rdf:resource="http://www.w3.org/ns/dcat#Dataset"/>
    <dct:type rdf:resource="http://purl.org/dc/dcmitype/Dataset"/>
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.2593266</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.2593266"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-5061-9018">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Dimitris Mitropoulos</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Athens University of Economics and Business</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-3971-4612">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Panos Louridas</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Athens University of Economics and Business</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Vitalis Salis</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Greek Research and Technology Network</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0003-4231-1897">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Diomidis Spinellis</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Athens University of Economics and Business</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>All Your Script Are Belong to Us: Collecting and Analyzing JavaScript Code from 10K Sites for 9 Months</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2019</dct:issued>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2019-03-14</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/2593266"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/2593266</skos:notation>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.2593265"/>
    <dct:description>&lt;p&gt;We present a massive dataset (~2 TB) of client-side JavaScript code. Specifically, we have collected and stored on adaily basis JavaScript code from Alexa&amp;#39;s Top 10000 web sites (~7.5 GB per day) for nine consecutive months. Our collection involved both inline scripts extracted from each web site&amp;#39;s main page and external scripts linked from it. In order to aid researchers identify similar scripts and examine their popularity and evolution, we have produced hashes that represent the scripts&amp;#39; logical structure. Furthermore, we have analyzed the resulting dataset with well-established static analysis tools, generating additional metadata including reports with quality bugs and vulnerable libraries.&lt;/p&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dcat:distribution>
      <dcat:Distribution>
        <dct:license rdf:resource="http://creativecommons.org/licenses/by/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.2593266"/>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>
82
10
views
downloads
All versions This version
Views 8282
Downloads 1010
Data volume 363.5 GB363.5 GB
Unique views 7373
Unique downloads 66

Share

Cite as