An approach for failure recognition in IP-based industrial control networks and systems

2012 ◽  
Vol 22 (6) ◽  
pp. 477-493 ◽  
Author(s):  
Youngjoon Won ◽  
Mi-Jung Choi ◽  
Byungchul Park ◽  
James Won-Ki Hong
Keyword(s):  
Industrial Control ◽  
Control Networks ◽  
Industrial Control Networks

A Guide to Securing Industrial Control Networks: Integrating IT and OT Systems

2020 ◽  
Vol 26 (2) ◽  
pp. 47-53
Author(s):  
Richard Paes ◽  
David C. Mazur ◽  
Bruce K. Venne ◽  
Jack Ostrzenski
Keyword(s):  
Industrial Control ◽  
Control Networks ◽  
Industrial Control Networks

Anomaly Detection for Industrial Control Networks Based on Improved One-Class Support Vector Machine

2020 ◽  
pp. 2150012
Author(s):  
Haicheng Qu ◽  
Jianzhong Zhou ◽  
Jitao Qin ◽  
Xiaorong Tian
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Anomaly Detection ◽  
Support Vector ◽  
Industrial Control ◽  
Control Networks ◽  
Detection Algorithms ◽  
Hinge Loss ◽  
Feature Fitting ◽  
Industrial Control Networks

In traditional network anomaly detection algorithms, the anomaly threshold needs to be defined manually. Keeping this as background, this study proposes an anomaly detection algorithm (VAEOCSVM), which combines the variable auto-encoder (VAE) and one-class support vector machine (OCSVM) to realize anomaly detection in industrial control networks. First, the VAE model is used to obtain the distribution of the original normal sample data represented by the low-dimensional code; the reconstruction error of the VAE model is merged into the new input. Then, using OCSVM’s hinge-loss objective function and the random Fourier feature fitting radial basis function (RBF) kernel method, the OCSVM model is represented and solved using the deep neural network and gradient descent method. Finally, the decision function of the OCSVM model is constructed by using the solved parameter information to realize the detection of abnormal data. The proposed algorithm is compared with other machine-learning-based anomaly detection algorithms in terms of multiple indicators such as precision, recall, and [Formula: see text] score. The experimental results using various datasets show that the proposed algorithm has a better outlier recognition ability than the machine-learning-based anomaly detection algorithms.

Sign in / Sign up

Export Citation Format

Share Document