• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Development of a Self Machine Learning System for Fast Detection of Intrusions to Next Generation in-Vehicle Network

Research Project

Project/Area Number 19K11881
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 60040:Computer system-related
Research InstitutionHiroshima City University

Principal Investigator

Nagayama Shinobu  広島市立大学, 情報科学研究科, 教授 (10405491)

Project Period (FY) 2019-04-01 – 2023-03-31
Project Status Completed (Fiscal Year 2022)
Budget Amount *help
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2022: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2021: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2020: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2019: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Keywordsプログラマブルシステム / ネットワークセキュリティ / ネットワーク侵入検知システム / 機械学習 / 決定グラフ / 論理設計 / 多値論理
Outline of Research at the Start

本研究では,車載ネットワークへの不正侵入を高速に検知・防止するシステムを開発し,当該システムの詳細な性能評価により,その実用可能性を明らかにする.開発するシステムはランダムフォレストという機械学習に基づいているため,新たな不正侵入の手口をシステム自らが学習する自己学習機能を備えた自律システムを開発する.サイズやコスト,消費電力などの厳しい制約を満足するために,決定グラフを用いた設計手法により,ワンチップでの専用ハードウェアでシステムを実現する.

Outline of Final Research Achievements

In this study, we developed an in-vehicle network intrusion detection system (NIDS) and its computer aided design tools. The developed system is based on a hybrid type using signature-based detection and anomaly detection in a complementary manner. In the system, both signature-based detection and anomaly detection are realized with tree-based hardware, and thus, it achieves high-speed detection and compact size. Since we have already developed a fast circuit for signature-based detection that can achieve 11 to 23 times faster than software-based NIDSs in our previous study, we focused on development of a circuit for anomaly detection in this study. By making tree-based hardware multiple-valued, we confirmed that it is possible to shorten processing time in 40% and reduce size in 20%.

Academic Significance and Societal Importance of the Research Achievements

本研究では,機械学習(いわゆるAI)によって,車載ネットワークへのハッキングなどの不正侵入を高速に検知するシステムを開発した.AIでの計算部分に多値決定グラフの技術を用いることで,処理の高速化だけでなく,車載などの組込み機器に必須となるサイズ削減も達成できた.新たな侵入手口にも柔軟に対応できる仕組みも備えているため,機器へのネットワークを介した不正侵入における安全性と利便性の両立が可能になった.当研究では,システムの設計・最適化手法も合わせて開発したため,車載機器に限らず,様々なIoT機器に応用することができ,当該技術の応用が進めば,より安全で快適なIoT社会が実現されるだろう.

Report

(5 results)
  • 2022 Annual Research Report   Final Research Report ( PDF )
  • 2021 Research-status Report
  • 2020 Research-status Report
  • 2019 Research-status Report
  • Research Products

    (31 results)

All 2022 2021 2020 2019 Other

All Int'l Joint Research (4 results) Journal Article (8 results) (of which Int'l Joint Research: 6 results,  Peer Reviewed: 8 results) Presentation (18 results) (of which Int'l Joint Research: 5 results,  Invited: 2 results) Remarks (1 results)

  • [Int'l Joint Research] Naval Postgraduate School(米国)

    • Related Report
      2022 Annual Research Report
  • [Int'l Joint Research] Naval Postgraduate School(米国)

    • Related Report
      2021 Research-status Report
  • [Int'l Joint Research] Naval Postgraduate School(米国)

    • Related Report
      2020 Research-status Report
  • [Int'l Joint Research] Naval Postgraduate School(米国)

    • Related Report
      2019 Research-status Report
  • [Journal Article] A Proposal of Equivalence Classes for Index Generation Functions Based on Their Row-Shift Decompositions2022

    • Author(s)
      Rie Kometani, Shinobu Nagayama,Masato Inagi, Shin'ichi Wakabayashi
    • Journal Title

      Proceedings of International Workshop on Post-Binary ULSI Systems

      Volume: 31 Pages: 9-9

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed
  • [Journal Article] On Decision Diagrams for Maximally Asymmetric Functions2022

    • Author(s)
      Nagayama Shinobu、Sasao Tsutomu、Butler Jon T.
    • Journal Title

      Proceedings of IEEE International Symposium on Multiple-Valued Logic

      Volume: 52 Pages: 164-169

    • DOI

      10.1109/ismvl52857.2022.00032

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] A Fast Method for Exactly Optimum Linear Decomposition of Index Generation Functions2022

    • Author(s)
      Shinobu Nagayama, Tsutomu Sasao, Jon T. Butler
    • Journal Title

      Journal of Multiple-Valued Logic and Soft Computing

      Volume: 38 Pages: 387-405

    • Related Report
      2022 Annual Research Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Improvement in the Quality of Solutions of a Heuristic Linear Decomposer for Index Generation Functions2021

    • Author(s)
      Nagayama Shinobu、Sasao Tsutomu、Butler Jon T.
    • Journal Title

      Proceedings of IEEE International Symposium on Multiple-Valued Logic

      Volume: 51 Pages: 13-18

    • DOI

      10.1109/ismvl51352.2021.00012

    • Related Report
      2021 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] On a Generation Method of Benchmark Maximally Asymmetric Functions2020

    • Author(s)
      Shinobu Nagayama, Hiroshi Kanehagi, Masato Inagi, Shin’ichi Wakabayashi
    • Journal Title

      Proceedings of International Workshop on Post-Binary ULSI Systems

      Volume: 29 Pages: 36-41

    • Related Report
      2020 Research-status Report
    • Peer Reviewed
  • [Journal Article] On Optimum Linear Decomposition of Symmetric Index Generation Functions2020

    • Author(s)
      Nagayama Shinobu、Sasao Tsutomu、Butler Jon T.
    • Journal Title

      Proceedings of IEEE International Symposium on Multiple-Valued Logic

      Volume: 50 Pages: 130-136

    • DOI

      10.1109/ismvl49045.2020.00-17

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] Properties of Multiple-Valued Partition Functions2020

    • Author(s)
      Butler Jon T.、Sasao Tsutomu、Nagayama Shinobu
    • Journal Title

      Proceedings of IEEE International Symposium on Multiple-Valued Logic

      Volume: 50 Pages: 82-87

    • DOI

      10.1109/ismvl49045.2020.00-25

    • Related Report
      2020 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Journal Article] A Dynamic Programming Based Method for Optimum Linear Decomposition of Index Generation Functions2019

    • Author(s)
      Nagayama Shinobu、Sasao Tsutomu、Butler Jon T.
    • Journal Title

      Proceedings of IEEE International Symposium on Multiple-Valued Logic

      Volume: 49 Pages: 144-149

    • DOI

      10.1109/ismvl.2019.00033

    • Related Report
      2019 Research-status Report
    • Peer Reviewed / Int'l Joint Research
  • [Presentation] On Decision Diagrams for Maximally Asymmetric Functions2022

    • Author(s)
      Shinobu Nagayama
    • Organizer
      IEEE International Symposium on Multiple-Valued Logic
    • Related Report
      2022 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 多値決定木に基づく Hyper Spectral 画像内の異常検出に関する一検討2022

    • Author(s)
      若嵜頌平, 永山忍,稲木雅人, 若林真一
    • Organizer
      第45回 多値論理フォーラム
    • Related Report
      2022 Annual Research Report
  • [Presentation] 対称インデックス生成関数における行シフト分解可能性について2022

    • Author(s)
      米谷理絵, 永山忍,稲木雅人, 若林真一
    • Organizer
      第45回 多値論理フォーラム
    • Related Report
      2022 Annual Research Report
  • [Presentation] Improvement in the Quality of Solutions of a Heuristic Linear Decomposer for Index Generation Functions2021

    • Author(s)
      Shinobu Nagayama
    • Organizer
      IEEE International Symposium on Multiple-Valued Logic
    • Related Report
      2021 Research-status Report
    • Int'l Joint Research
  • [Presentation] ナンバーリンク問題例の効率的な自動生成手法について2021

    • Author(s)
      中島圭一、永山忍
    • Organizer
      第44回 多値論理フォーラム
    • Related Report
      2021 Research-status Report
  • [Presentation] On a Generation Method of Benchmark Maximally Asymmetric Functions2020

    • Author(s)
      Shinobu Nagayama
    • Organizer
      International Workshop on Post-Binary ULSI Systems
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] On Optimum Linear Decomposition of Symmetric Index Generation Functions2020

    • Author(s)
      Shinobu Nagayama
    • Organizer
      IEEE International Symposium on Multiple-Valued Logic
    • Related Report
      2020 Research-status Report
    • Int'l Joint Research
  • [Presentation] 最大非対称多値関数の判定法と生成法の提案2020

    • Author(s)
      永山忍
    • Organizer
      第43回 多値論理フォーラム
    • Related Report
      2020 Research-status Report
  • [Presentation] 最大非対称関数の特徴分析とその生成について2020

    • Author(s)
      金羽木洋志、永山忍
    • Organizer
      電子情報通信学会 VLSI 設計技術研究会
    • Related Report
      2020 Research-status Report
  • [Presentation] Isolation Forestによる異常検知の効率化に関する検討2020

    • Author(s)
      池田翼、永山忍
    • Organizer
      電子情報通信学会 VLSI 設計技術研究会
    • Related Report
      2019 Research-status Report
  • [Presentation] EVBDDに基づく初等関数回路の設計検証2020

    • Author(s)
      福原浩人、永山忍
    • Organizer
      電子情報通信学会 VLSI 設計技術研究会
    • Related Report
      2019 Research-status Report
  • [Presentation] インデックス生成関数の行シフト分解における分解可能性判定法2020

    • Author(s)
      常定京一郎、永山忍
    • Organizer
      電子情報通信学会 VLSI 設計技術研究会
    • Related Report
      2019 Research-status Report
  • [Presentation] 行シフト分解に基づくインデックス生成関数の同値類について2020

    • Author(s)
      永山忍
    • Organizer
      第33回 多値論理とその応用研究会
    • Related Report
      2019 Research-status Report
  • [Presentation] 次世代自動車の開発を陰で支える情報科学技術2019

    • Author(s)
      永山忍
    • Organizer
      明治大学 特別講義
    • Related Report
      2019 Research-status Report
    • Invited
  • [Presentation] インデックス生成関数の行シフト分解における分解可能性について2019

    • Author(s)
      常定京一郎、永山忍
    • Organizer
      第42回 多値論理フォーラム
    • Related Report
      2019 Research-status Report
  • [Presentation] Isolation Forest の多値化に関する検討2019

    • Author(s)
      池田翼、永山忍
    • Organizer
      第42回 多値論理フォーラム
    • Related Report
      2019 Research-status Report
  • [Presentation] A Dynamic Programming Based Method for Optimum Linear Decomposition of Index Generation Functions2019

    • Author(s)
      Shinobu Nagayama
    • Organizer
      IEEE International Symposium on Multiple-Valued Logic
    • Related Report
      2019 Research-status Report
    • Int'l Joint Research
  • [Presentation] 良く似たデータを素早く探せ! - 類似・近似データ探索の高速化について -2019

    • Author(s)
      永山忍
    • Organizer
      明治大学 特別講義
    • Related Report
      2019 Research-status Report
    • Invited
  • [Remarks] 広島市立大学 情報科学研究科 情報工学専攻 永山忍

    • URL

      http://rsw.office.hiroshima-cu.ac.jp/Profiles/8/0000731/profile.html

    • Related Report
      2022 Annual Research Report 2021 Research-status Report 2020 Research-status Report 2019 Research-status Report

URL: 

Published: 2019-04-18   Modified: 2024-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi