logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

CUTIE: Component-specific Unsupervised Technique for In-node Examination

delete2026-04-27
delete0
PRE
AI
A
Andrea Vignali *
N
Nicola d’Ambrosio
DOI：10.1016/j.comnet.2026.112339delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• CUTIE is a distributed framework of lightweight IDS modules deployed on PLCs. • CUTIE modules are trained in an unsupervised way on their respective PLC baselines. • CUTIE effectiveness and efficiency are evaluated on the SWaT dataset using 4 modules. • CUTIE achieved a high normal-class F1-score with low attack detection latency.
Keywords:
Industrial control systems
Anomaly detection
Unsupervised machine learning
Cyber-physical systems
AI Summary

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.

Journal

Computer Networks cover
Computer Networks
IF:
4.6
Papers:
1.5K
Citations:
1.6W

Organization

No organization information available