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

TLDR

Industry 4.0 has spurred widespread use of AI and smart techniques in industrial cyber‑physical systems, yet detecting cyber‑physical attacks remains difficult, especially when only few labeled examples are available. This study introduces a few‑shot learning model based on a Siamese convolutional neural network to reduce over‑fitting and boost accuracy in intelligent anomaly detection for industrial CPS. The approach employs a Siamese CNN encoder that computes distances between samples using optimized feature representations, a robust cost function comprising three specific losses, and culminates in an anomaly‑detection algorithm. Experiments on a fully labeled public dataset and a few‑label dataset demonstrate that the proposed FSL‑SCNN markedly lowers false‑alarm rates and raises F1 scores for intrusion signal detection in industrial CPS.

Abstract

With the increasing population of Industry 4.0, both AI and smart techniques have been applied and become hotly discussed topics in industrial cyber-physical systems (CPS). 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 article, we propose a few-shot learning model with Siamese convolutional neural network (FSL-SCNN), to alleviate the over-fitting issue and enhance the accuracy for intelligent anomaly detection in industrial CPS. 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 FSL-SCNN can significantly improve false alarm rate (FAR) and F1 scores when detecting intrusion signals for industrial CPS security protection.