Automatic labeling of the elements of a vulnerability report CVE with NLP

Kensuke Sumoto, Kenta Kanakogi, Hironori Washizaki, Naohiko Tsuda, Nobukazu Yoshioka, Yoshiaki Fukazawa, Hideyuki Kanuka

研究成果: Conference contribution

抄録

Common Vulnerabilities and Exposures (CVE) databases contain information about vulnerabilities of software products and source code. If individual elements of CVE descriptions can be extracted and structured, then the data can be used to search and analyze CVE descriptions. Herein we propose a method to label each element in CVE descriptions by applying Named Entity Recognition (NER). For NER, we used BERT, a transformer-based natural language processing model. Using NER with machine learning can label information from CVE descriptions even if there are some distortions in the data. An experiment involving manually prepared label information for 1000 CVE descriptions shows that the labeling accuracy of the proposed method is about 0.81 for precision and about 0.89 for recall. In addition, we devise a way to train the data by dividing it into labels. Our proposed method can be used to label each element automatically from CVE descriptions.

本文言語English
ホスト出版物のタイトルProceedings - 2022 IEEE 23rd International Conference on Information Reuse and Integration for Data Science, IRI 2022
出版社Institute of Electrical and Electronics Engineers Inc.
ページ164-165
ページ数2
ISBN(電子版)9781665466035
DOI
出版ステータスPublished - 2022
イベント23rd IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2022 - Virtual, Online, United States
継続期間: 2022 8月 92022 8月 11

出版物シリーズ

名前Proceedings - 2022 IEEE 23rd International Conference on Information Reuse and Integration for Data Science, IRI 2022

Conference

Conference23rd IEEE International Conference on Information Reuse and Integration for Data Science, IRI 2022
国/地域United States
CityVirtual, Online
Period22/8/922/8/11

ASJC Scopus subject areas

  • 人工知能
  • コンピュータ サイエンスの応用
  • コンピュータ ビジョンおよびパターン認識
  • 決定科学(その他)
  • 情報システムおよび情報管理
  • 安全性、リスク、信頼性、品質管理

フィンガープリント

「Automatic labeling of the elements of a vulnerability report CVE with NLP」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