Dataset Open Access

HYDRA dataset

Fran Casino; Nikolaos Lykousas; Ivan Homoliak; Constantinos Patsakis; Julio Hernandez-Castro


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: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.3965397">
    <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.3965397</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.3965397"/>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0003-4296-2876">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0003-4296-2876</dct:identifier>
        <foaf:name>Fran Casino</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Piraeus</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0001-8874-1230">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0001-8874-1230</dct:identifier>
        <foaf:name>Nikolaos Lykousas</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Piraeus</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-0790-0875">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-0790-0875</dct:identifier>
        <foaf:name>Ivan Homoliak</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>Brno University of Technology</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-4460-9331">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-4460-9331</dct:identifier>
        <foaf:name>Constantinos Patsakis</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Piraeus</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:creator>
      <rdf:Description rdf:about="http://orcid.org/0000-0002-6432-5328">
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">0000-0002-6432-5328</dct:identifier>
        <foaf:name>Julio Hernandez-Castro</foaf:name>
        <org:memberOf>
          <foaf:Organization>
            <foaf:name>University of Kent</foaf:name>
          </foaf:Organization>
        </org:memberOf>
      </rdf:Description>
    </dct:creator>
    <dct:title>HYDRA dataset</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">2020</dct:issued>
    <dcat:keyword>Domain generation algorithms</dcat:keyword>
    <dcat:keyword>DGA</dcat:keyword>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/832735/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/780498/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <frapo:isFundedBy rdf:resource="info:eu-repo/grantAgreement/EC/H2020/830929/"/>
    <schema:funder>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </schema:funder>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2020-07-29</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/3965397"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/3965397</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.3965396"/>
    <owl:versionInfo>1.0</owl:versionInfo>
    <dct:description>&lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;p&gt;This repository contains a large dataset for the research of domain generation algorithms (DGAs) and machine learning. At the time of writing the dataset contains more than 90m of domains and more than 100 families.&lt;/p&gt; &lt;p&gt;The dataset consists of SLDs from DGAs and their extracted features. The main sources for the DGAs are the following:&lt;/p&gt; &lt;ul&gt; &lt;li&gt;&lt;a href="https://dgarchive.caad.fkie.fraunhofer.de/"&gt;DGArchive&lt;/a&gt;&lt;/li&gt; &lt;li&gt;&lt;a href="https://data.netlab.360.com/dga/"&gt;The DGA feed from Network Security Research Lab at 360&lt;/a&gt;&lt;/li&gt; &lt;li&gt;&lt;a href="http://osint.bambenekconsulting.com/feeds/"&gt;The OSINT feeds for DGA from Bambenek Consulting&lt;/a&gt;&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;When the samples were sparse, we used the reversed code to create new ones.&lt;/p&gt; &lt;ul&gt; &lt;li&gt;&lt;a href="https://github.com/baderj/domain_generation_algorithms"&gt;Johannes Bader Github repo&lt;/a&gt;&lt;/li&gt; &lt;/ul&gt; &lt;p&gt;Moreover, it has SLDs from three adversarial DGAs (referred to deception, deception2 and khaos) DGAs and SLDs from the top 1m Alexa domains.&lt;/p&gt; &lt;p&gt;Features by the order they appear in the dataset&lt;/p&gt; &lt;ul&gt; &lt;li&gt;Family: DGA Family&lt;/li&gt; &lt;li&gt;SLD: SLD of the domain&lt;/li&gt; &lt;li&gt;L-HEX: The domain name is represented with hexadecimal characters&lt;/li&gt; &lt;li&gt;L-LEN: The length of Dom&lt;/li&gt; &lt;li&gt;L-DIG: The number of digits in Dom&lt;/li&gt; &lt;li&gt;L-DOT: The number of dots in the raw domain&lt;/li&gt; &lt;li&gt;L-CON-MAX: The maximum number of consecutive consonants Dom&lt;/li&gt; &lt;li&gt;L-VOW-MAX: The maximum number of consecutive vowels Dom&lt;/li&gt; &lt;li&gt;L-W2: Number of words with more than 2 characters in Dom&lt;/li&gt; &lt;li&gt;L-W3: Number of words with more than 3 characters in Dom&lt;/li&gt; &lt;li&gt;R-CON-VOW: Ratio of consonants and vowels ofDom&lt;/li&gt; &lt;li&gt;R-Dom-3G: Ratio of benign grams in Dom-3G&lt;/li&gt; &lt;li&gt;R-Dom-4G: Ratio of benign grams in Dom-4G&lt;/li&gt; &lt;li&gt;R-Dom-5G: Ratio of benign grams in Dom-5G&lt;/li&gt; &lt;li&gt;R-VOW-3G: Ratio of grams that contain a vowel in Dom-3G&lt;/li&gt; &lt;li&gt;R-VOW-4G: Ratio of grams that contain a vowel in Dom-4G&lt;/li&gt; &lt;li&gt;R-VOW-5G: Ratio of grams that contain a vowel in Dom-5G&lt;/li&gt; &lt;li&gt;R-WS-LEN: Dom-WS divided by L-LEN&lt;/li&gt; &lt;li&gt;R-WD-LEN: Dom-WD divided by L-LEN&lt;/li&gt; &lt;li&gt;R-WDS-LEN: Dom-WDS divided by L-LEN&lt;/li&gt; &lt;li&gt;R-W2-LEN: Dom-W2 divided by L-LEN&lt;/li&gt; &lt;li&gt;R-W2-LEN-D: Dom-W2 divided by Dom-D&lt;/li&gt; &lt;li&gt;R-W3-LEN: Dom-W3 divided by L-LEN&lt;/li&gt; &lt;li&gt;R-W3-LEN-D: Dom-W3 divided by Dom-D&lt;/li&gt; &lt;li&gt;GIB-1-Dom: Gibberish detector 1 applied to Dom&lt;/li&gt; &lt;li&gt;GIB-1-Dom-WS: Gibberish detector 1 applied to Dom-WS&lt;/li&gt; &lt;li&gt;GIB-1-Dom-D: Gibberish detector 1 applied to Dom-D&lt;/li&gt; &lt;li&gt;GIB-1-Dom-WDS: Gibberish detector 1 applied to Dom-WDS&lt;/li&gt; &lt;li&gt;GIB-1-Dom-W2: Gibberish detector 1 applied to Dom-W2&lt;/li&gt; &lt;li&gt;GIB-1-Dom-W3: Gibberish detector 1 applied to Dom-W3&lt;/li&gt; &lt;li&gt;GIB-2-Dom: Gibberish detector 2 applied to Dom&lt;/li&gt; &lt;li&gt;GIB-2-Dom-WS: Gibberish detector 2 applied to Dom-WS&lt;/li&gt; &lt;li&gt;GIB-2-Dom-D: Gibberish detector 2 applied to Dom-D&lt;/li&gt; &lt;li&gt;GIB-2-Dom-WDS: Gibberish detector 2 applied to Dom-WDS&lt;/li&gt; &lt;li&gt;GIB-2-Dom-W2: Gibberish detector 2 applied to Dom-W2&lt;/li&gt; &lt;li&gt;GIB-2-Dom-W3: Gibberish detector 2 applied to Dom-W3&lt;/li&gt; &lt;li&gt;E-Dom: Entropy ofDom&lt;/li&gt; &lt;li&gt;E-Dom-WS: Entropy of Dom-WS&lt;/li&gt; &lt;li&gt;E-Dom-D: Entropy of Dom-D&lt;/li&gt; &lt;li&gt;E-Dom-WDS: Entropy of Dom-WDS&lt;/li&gt; &lt;li&gt;E-Dom-W2: Entropy of Dom-W2&lt;/li&gt; &lt;li&gt;E-Dom-W3: Entropy of Dom-W3&lt;/li&gt; &lt;/ul&gt;</dct:description>
    <dct:description>{"references": ["Plohmann, Daniel, et al. \"A comprehensive measurement study of domain generating malware.\" 25th USENIX Security Symposium (USENIX\u00a0Security 16). 2016.", "X. Yun, J. Huang, Y. Wang, T. Zang, Y. Zhou, and Y. Zhang, \"Khaos: An \u00a0adversarial \u00a0neural \u00a0network \u00a0dga \u00a0with \u00a0high \u00a0anti-detection \u00a0ability\", IEEE Transactions on Information Forensics and Security, vol. 15, pp.2225\u20132240, 2020.", "Spooren, Jan, et al. \"Detection of algorithmically generated domain names used by botnets: a dual arms race.\" Proceedings of the 34th ACM/SIGAPP Symposium on Applied Computing. 2019."]}</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="https://creativecommons.org/licenses/by/4.0/legalcode"/>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.3965397"/>
      </dcat:Distribution>
    </dcat:distribution>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL>https://doi.org/10.5281/zenodo.3965397</dcat:accessURL>
        <dcat:byteSize>2699517421</dcat:byteSize>
        <dcat:downloadURL>https://zenodo.org/record/3965397/files/dataset.7z</dcat:downloadURL>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/832735/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">832735</dct:identifier>
    <dct:title>Lawful evidence collecting and continuity platform development</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/780498/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">780498</dct:identifier>
    <dct:title>Cybersecurity Awareness and Knowledge Systemic High-level Application</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
  <foaf:Project rdf:about="info:eu-repo/grantAgreement/EC/H2020/830929/">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">830929</dct:identifier>
    <dct:title>Cyber Security Network of Competence Centres for Europe</dct:title>
    <frapo:isAwardedBy>
      <foaf:Organization>
        <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#string">10.13039/501100000780</dct:identifier>
        <foaf:name>European Commission</foaf:name>
      </foaf:Organization>
    </frapo:isAwardedBy>
  </foaf:Project>
</rdf:RDF>
243
52
views
downloads
All versions This version
Views 243243
Downloads 5252
Data volume 140.4 GB140.4 GB
Unique views 219219
Unique downloads 2828

Share

Cite as