<?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>2026-03-09T16:02:58Z</responseDate>
  <request metadataPrefix="jpcoar_1.0" verb="GetRecord" identifier="oai:ipsj.ixsq.nii.ac.jp:00240802">https://ipsj.ixsq.nii.ac.jp/oai</request>
  <GetRecord>
    <record>
      <header>
        <identifier>oai:ipsj.ixsq.nii.ac.jp:00240802</identifier>
        <datestamp>2025-03-06T05:32:07Z</datestamp>
        <setSpec>6164:6165:6462:11854</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 xml:lang="ja">LiDAR 点群の物理的消失による誤検出誘発攻撃と防御</dc:title>
          <dc:title xml:lang="en">Disrupting LiDAR Object Detection by Physically Removing Point Clouds and Developing Defense</dc:title>
          <jpcoar:creator>
            <jpcoar:creatorName>小林, 竜之輔</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>野本, 一輝</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>田中, 優奈</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>鶴岡, 豪</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName>森, 達哉</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Ryunosuke, Kobayashi</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Kazuki, Nomoto</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Yuna, Tanaka</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Go, Tsuruoka</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:creator>
            <jpcoar:creatorName xml:lang="en">Tatsuya, Mori</jpcoar:creatorName>
          </jpcoar:creator>
          <jpcoar:subject subjectScheme="Other">自動運転，LiDAR，物体検出，敵対的サンプル</jpcoar:subject>
          <datacite:description descriptionType="Other">自動運転車に搭載されている LiDAR は，安全な車両制御のためのリアルタイム意思決定に不可欠なセンサである．しかし，自動運転車の LiDAR への依存が高まるにつれて，LiDAR に対する攻撃のリスクが懸念されている．本研究では，LiDAR 物体検出に対する新たな攻撃手法として「シャドウハック」を提案する．この攻撃は，鏡面反射する素材を用いて LiDAR が計測できない領域，敵対的シャドウを生成し，物体検出モデルに存在しない物体を誤検出させるものである．現実世界での実験では，PointPillarsに対して 10 m で 100%，15 m で 66% の攻撃成功率を達成した．また，シミュレーションにより，異なる LiDAR や物体検出モデルに対するシャドウハックの頑健性を確認した．最後に，防御メカニズムとして BBValidator を開発し，物体検出精度への影響を 0.1 未満に抑えつつ，100% の防御成功率を達成した．</datacite:description>
          <datacite:description descriptionType="Other">LiDAR installed in autonomous vehicles is an essential sensor for real-time decision-making required for safe vehicle control. However, as reliance on LiDAR in autonomous vehicles increases, the risk of attacks targeting LiDAR is becoming a significant concern. In this study, we propose a novel attack method against LiDAR-based object detection called “Shadow Hack.” This attack uses reflective materials to create adversarial shadows in areas that LiDAR cannot accurately measure, leading to the misidentification of non-existent objects by the object detection model. In real-world experiments, we achieved a 100% attack success rate at a distance of 10 meters and a 66% success rate at 15 meters against the PointPillars model. Additionally, simulations confirmed the robustness of Shadow Hack across different LiDAR systems and object detection models. Finally, we developed a defense mechanism called “BBValidator,” which achieved a 100% defense success rate while maintaining an impact on object detection accuracy of less than 0.1.</datacite:description>
          <dc:publisher xml:lang="ja">情報処理学会</dc:publisher>
          <datacite:date dateType="Issued">2024-10-15</datacite:date>
          <dc:language>jpn</dc:language>
          <dc:type rdf:resource="http://purl.org/coar/resource_type/c_5794">conference paper</dc:type>
          <jpcoar:identifier identifierType="URI">https://ipsj.ixsq.nii.ac.jp/records/240802</jpcoar:identifier>
          <jpcoar:sourceTitle>コンピュータセキュリティシンポジウム2024論文集</jpcoar:sourceTitle>
          <jpcoar:pageStart>409</jpcoar:pageStart>
          <jpcoar:pageEnd>416</jpcoar:pageEnd>
          <jpcoar:file>
            <jpcoar:URI label="IPSJ-CSS2024056.pdf">https://ipsj.ixsq.nii.ac.jp/record/240802/files/IPSJ-CSS2024056.pdf</jpcoar:URI>
            <jpcoar:mimeType>application/pdf</jpcoar:mimeType>
            <jpcoar:extent>3.6 MB</jpcoar:extent>
            <datacite:date dateType="Available">2026-10-15</datacite:date>
          </jpcoar:file>
        </jpcoar:jpcoar>
      </metadata>
    </record>
  </GetRecord>
</OAI-PMH>
