A New Approach for Machine Learning Security Risk Assessment - Work in Progress

Jun Yajima, Maki Inui, Takanori Oikawa, Fumiyoshi Kasahara, Ikuya Morikawa, Nobukazu Yoshioka

研究成果: Conference contribution

抄録

We propose a new security risk assessment approach for Machine Learning-based AI systems (ML systems). The assessment of security risks of ML systems requires expertise in ML security. So, ML system developers, who may not know much about ML security, cannot assess the security risks of their systems. By using our approach, a ML system developers can easily assess the security risks of the ML system. In performing the assessment, the ML system developer only has to answer the yes/no questions about the specification of the ML system. In our trial, we confirmed that our approach works correctly.

本文言語English
ホスト出版物のタイトルProceedings - 1st International Conference on AI Engineering - Software Engineering for AI, CAIN 2022
出版社Institute of Electrical and Electronics Engineers Inc.
ページ52-53
ページ数2
ISBN(電子版)9781450392754
DOI
出版ステータスPublished - 2022
イベント1st International Conference on AI Engineering - Software Engineering for AI, CAIN 2022 - Pittsburgh, United States
継続期間: 2022 5月 162022 5月 17

出版物シリーズ

名前Proceedings - 1st International Conference on AI Engineering - Software Engineering for AI, CAIN 2022

Conference

Conference1st International Conference on AI Engineering - Software Engineering for AI, CAIN 2022
国/地域United States
CityPittsburgh
Period22/5/1622/5/17

ASJC Scopus subject areas

  • 人工知能
  • ソフトウェア

フィンガープリント

「A New Approach for Machine Learning Security Risk Assessment - Work in Progress」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル