<?xml version='1.0' encoding='UTF-8'?>
<OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd">
  <responseDate>2026-03-15T10:58:13Z</responseDate>
  <request metadataPrefix="jpcoar_1.0" verb="GetRecord" identifier="oai:ipsj.ixsq.nii.ac.jp:00216992">https://ipsj.ixsq.nii.ac.jp/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:ipsj.ixsq.nii.ac.jp:00216992</identifier>
        <datestamp>2025-01-19T15:39:53Z</datestamp>
        <setSpec>1164:2836:10841:10842</setSpec>
      </header>
      <metadata>
        <jpcoar:jpcoar xmlns:datacite="https://schema.datacite.org/meta/kernel-4/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dcndl="http://ndl.go.jp/dcndl/terms/" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:jpcoar="https://github.com/JPCOAR/schema/blob/master/1.0/" xmlns:oaire="http://namespace.openaire.eu/schema/oaire/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:rioxxterms="http://www.rioxx.net/schema/v2.0/rioxxterms/" xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns="https://github.com/JPCOAR/schema/blob/master/1.0/" xsi:schemaLocation="https://github.com/JPCOAR/schema/blob/master/1.0/jpcoar_scm.xsd">
          <dc:title>メタ学習に基づくFew-Shot分類に対するバックドアポイズニング攻撃</dc:title>
          <dc:title xml:lang="en">Backdoor Poisoning Attacks on Meta-Learned Few-Shot Classifiers</dc:title>
          <jpcoar:creator>
            <jpcoar:creatorName>加藤, 頑馬</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>高橋, 茶子</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>鈴木, 幸太郎</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Ganma, Kato</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Chako, Takahashi</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Koutarou, Suzuki</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:subject subjectScheme="Other">攻撃検知・機械学習セキュリティ</jpcoar:subject>
          <datacite:description descriptionType="Other">教師データが少ない状況での分類は few-shot 分類と呼ばれ，その主要な実現方法の一つにメタ学習 (meta-learning) が知られている．Few-shot分類はさまざまな分野で実応用が検討され始めているが，敵対的攻撃や防御策についてはまだ十分に調べられていない．特に，メタ学習に基づく few-shot 分類に対するポイズニング攻撃についての研究は始まって間もなく，可用性の侵害を目的としたポイズニングについては Xu et al. [1] および Oldewage et al. [2] によって調べられているものの，完全性の侵害を目的としたバックドアポイズニングについては Oldewage et al. [2] によって限られた条件での簡易的な評価が行われているのみである．本研究では，メタ学習に基づく few-shot 分類において完全性の侵害を目的とするバックドアポイズニング攻撃を定式化する．実験により，model-agnostic meta-learning (MAML)[3] を用いたメタ学習による few-shot 分類に対してバックドアポイズニング攻撃が有効であることを確認した．</datacite:description>
          <datacite:description descriptionType="Other">Few-shot classification is the classification with only a few samples, and meta-learning methods are often employed to solve it. Research on poisoning attacks against meta-learning-based few-shot classification is now in the very beginning. While poisoning to violate classifier's availability in meta-testing has been investigated in Xu et al. [1] and Oldewage et al. [2], backdoor poisoning in meta-testing has only been briefly evaluated by Oldewage et al. [2] under limited conditions. In this study, we formulate a backdoor poisoning attack on meta-learning-based few-shot classification. We show that the proposed backdoor poisoning attack is effective against the few-shot classification using model-agnostic meta-learning (MAML) [3] through experiments.</datacite:description>
          <dc:publisher xml:lang="ja">情報処理学会</dc:publisher>
          <datacite:date dateType="Issued">2022-03-03</datacite:date>
          <dc:language>jpn</dc:language>
          <dc:type rdf:resource="http://purl.org/coar/resource_type/c_18gh">technical report</dc:type>
          <jpcoar:identifier identifierType="URI">https://ipsj.ixsq.nii.ac.jp/records/216992</jpcoar:identifier>
          <jpcoar:sourceIdentifier identifierType="ISSN">2188-8906</jpcoar:sourceIdentifier>
          <jpcoar:sourceIdentifier identifierType="NCID">AN10116224</jpcoar:sourceIdentifier>
          <jpcoar:sourceTitle>研究報告マルチメディア通信と分散処理（DPS）</jpcoar:sourceTitle>
          <jpcoar:volume>2022-DPS-190</jpcoar:volume>
          <jpcoar:issue>8</jpcoar:issue>
          <jpcoar:pageStart>1</jpcoar:pageStart>
          <jpcoar:pageEnd>7</jpcoar:pageEnd>
          <jpcoar:file>
            <jpcoar:URI label="IPSJ-DPS22190008.pdf">https://ipsj.ixsq.nii.ac.jp/record/216992/files/IPSJ-DPS22190008.pdf</jpcoar:URI>
            <jpcoar:mimeType>application/pdf</jpcoar:mimeType>
            <jpcoar:extent>838.4 kB</jpcoar:extent>
            <datacite:date dateType="Available">2024-03-03</datacite:date>
          </jpcoar:file>
        </jpcoar:jpcoar>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
