<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "https://jats.nlm.nih.gov/publishing/1.3/JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xml:lang="en">
  <front xmlns:xlink="http://www.w3.org/1999/xlink">
    <journal-meta>
      <journal-id journal-id-type="elibrary">9004</journal-id>
      <journal-title-group>
        <journal-title>Problems of information security. Computer systems</journal-title>
        <trans-title-group xml:lang="ru">
          <trans-title>Проблемы информационной безопасности. Компьютерные системы</trans-title>
        </trans-title-group>
      </journal-title-group>
      <issn pub-type="epub">2071-8217</issn>
    </journal-meta>
    <article-meta xmlns:xlink="http://www.w3.org/1999/xlink">
      <article-id pub-id-type="publisher-id">8</article-id>
      <title-group>
        <article-title>Classification of methods to counteract a data poisoning attack during neural network training</article-title>
        <trans-title-group xml:lang="ru">
          <trans-title>Классификация методов противодействия атаке типа отравления данных при обучении нейронной сети</trans-title>
        </trans-title-group>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0003-0623-9891</contrib-id>
          <name>
            <surname>Gololobov</surname>
            <given-names>Nikita</given-names>
          </name>
          <xref ref-type="aff" rid="aff1"/>
          <email>gololobov_nv@spbstu.ru</email>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0003-1345-1874</contrib-id>
          <name>
            <surname>Pavlenko</surname>
            <given-names>Evgeny</given-names>
          </name>
          <xref ref-type="aff" rid="aff1"/>
          <email>pavlenko_eyu@spbstu.ru</email>
        </contrib>
      </contrib-group>
      <aff id="aff1">Peter the Great St. Petersburg Polytechnic University</aff>
      <pub-date publication-format="electronic" date-type="pub" iso-8601-date="2023-08-31">
        <day>31</day>
        <month>08</month>
        <year>2023</year>
      </pub-date>
      <issue>Спецвыпуск</issue>
      <fpage>86</fpage>
      <lpage>94</lpage>
      <self-uri xmlns:xlink="http://www.w3.org/1999/xlink" content-type="pdf" xlink:href="https://jisp.spbstu.ru/userfiles/files/soderzhaniya/2023_spetsvipusk_en_.pdf"/>
      <abstract xml:lang="en">
        <p>Considered methods of counteraction attack data poisoning type learning neural network and compiled a model of the attacker, according to which a classification of the considered methods. The classification obtained as a result of the study can be used in further research, the ultimate goal of which is to increase the level of unification and automation of data processing and protection methods.</p>
      </abstract>
      <kwd-group xml:lang="en">
        <kwd>information security</kwd>
        <kwd>machine learning</kwd>
        <kwd>data processing</kwd>
        <kwd>data poisoning</kwd>
        <kwd>learning quality</kwd>
      </kwd-group>
    </article-meta>
  </front>
</article>
