期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 17, 期 8, 页码 5790-5798出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.3047675
关键词
Anomaly detection; Security; Training; Task analysis; Feature extraction; Analytical models; Object recognition; Anomaly detection; convolutional neural network (CNN); few-shot learning; industrial cyber-physical systems (CPS); Siamese network
类别
资金
- National Key R&D Program of China [2017YFE0117500, 2019YFE0190500, 2019GK1010]
- National Natural Science Foundation of China [62072171]
- Natural Science Foundation of Hunan Province of China [2019JJ40150, 2018JJ2198]
This article proposes a few-shot learning model with Siamese convolutional neural network (FSL-SCNN) to enhance the accuracy of intelligent anomaly detection in industrial cyber-physical systems by alleviating over-fitting issues. Experimental results demonstrate that the proposed model can significantly improve the false alarm rate (FAR) and F1 scores in detecting intrusion signals for industrial CPS security protection.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据