Siamese Neural Network Based Few-Shot Learning for Anomaly Detection in Industrial Cyber-Physical Systems

Xiaokang Zhou, Wei Liang, Shohei Shimizu, Jianhua Ma, Qun Jin

Research output: Contribution to journalArticlepeer-review


Intelligent anomaly detection for identifying cyber/physical attacks to guarantee the work efficiency and safety is still a challenging issue, especially when dealing with few labeled data for cyber-physical security protection. In this study, we propose a few-shot learning model based on Siamese Convolution Neural Network (FS-SCNN), to alleviate the over-fitting issue and enhance the accuracy for intelligent anomaly detection in industrial CPSs. A Siamese CNN encoding network is constructed to measure distances of input samples based on their optimized feature representations. A robust cost function design including three specific losses is then proposed to enhance the efficiency of training process. An intelligent anomaly detection algorithm is developed finally. Experiment results based on a fully labeled public dataset and a few labeled dataset demonstrate that our proposed FS-SCNN can significantly improve FAR and F1 scores when detecting intrusion signals for industrial CPS security protection.

Original languageEnglish
JournalIEEE Transactions on Industrial Informatics
Publication statusAccepted/In press - 2020


  • Analytical models
  • Anomaly Detection
  • Anomaly detection
  • CNN
  • Feature extraction
  • Few-Shot Learning
  • Industrial CPS
  • Object recognition
  • Security
  • Siamese Network
  • Task analysis
  • Training

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Information Systems
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Siamese Neural Network Based Few-Shot Learning for Anomaly Detection in Industrial Cyber-Physical Systems'. Together they form a unique fingerprint.

Cite this