Behind the mask: Masquerading the reason for prediction

Tomohiro Koide, Masato Uchida

研究成果

抄録

Ensuring the interpretability of the machine-learning-based prediction models is important for gaining users’ trust. The current representative algorithms for ensuring interpretability, LIME and SHAP, explain the prediction of a given black-box machine learning model based on a common perturbation mechanism to input data. In this study, we propose a masquerade layer to nullify this perturbation and hide the reason for prediction. Our proposed masquerade layer can be attached to any prediction models. It can also be attached without altering the prediction model itself, making it possible to manipulate the explanation provided by the interpretability algorithm in a manner that hardly changes the prediction model behavior. The experimental results show that existing representative perturbation-based interpretability algorithms have a critical weaknesses in terms of their reliability.

本文言語English
ホスト出版物のタイトルProceedings - 2021 IEEE 45th Annual Computers, Software, and Applications Conference, COMPSAC 2021
編集者W. K. Chan, Bill Claycomb, Hiroki Takakura, Ji-Jiang Yang, Yuuichi Teranishi, Dave Towey, Sergio Segura, Hossain Shahriar, Sorel Reisman, Sheikh Iqbal Ahamed
出版社Institute of Electrical and Electronics Engineers Inc.
ページ475-481
ページ数7
ISBN(電子版)9781665424639
DOI
出版ステータスPublished - 2021 7
イベント45th IEEE Annual Computers, Software, and Applications Conference, COMPSAC 2021 - Virtual, Online, Spain
継続期間: 2021 7 122021 7 16

出版物シリーズ

名前Proceedings - 2021 IEEE 45th Annual Computers, Software, and Applications Conference, COMPSAC 2021

Conference

Conference45th IEEE Annual Computers, Software, and Applications Conference, COMPSAC 2021
国/地域Spain
CityVirtual, Online
Period21/7/1221/7/16

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ サイエンスの応用
  • ソフトウェア

フィンガープリント

「Behind the mask: Masquerading the reason for prediction」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