An Industrial Control Security Detection Method Based on Feature Expansion
A security detection and industrial control technology, applied in the field of industrial information security, can solve problems such as increasing the computational complexity of feature training, and achieve the effects of reducing the time complexity of feature computing, reducing feature weight offset, and improving training speed.
Active Publication Date: 2022-07-26
工业信息安全(四川)创新中心有限公司
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Most of its preprocessing modules are not feature selected, and its feature selection is selected for professional knowledge. Therefore, the preprocessing module will cause multi-dimensional useless features to affect other features, and also increase the computational complexity of feature training.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0038] All features disclosed in all embodiments in this specification, or steps in all methods or processes that are implicitly disclosed, except mutually exclusive features and / or steps, may be combined and / or expanded or replaced in any manner.
[0039] like Figures 1 to 6 As shown, an industrial control security detection method based on feature expansion includes the steps:
[0040] S1, select multiple pieces of characteristic data in the network connection data, and calculate the time t of a certain piece of characteristic data 0 The average time T of the first n pieces of data, n ≥ 4, construction time feature = data time t 0 -Average time T; the constructed time feature is used to construct a data matrix, and the constructed data matrix with time feature is used as a set of data; then operate as above to construct a second set of data for the next selected feature data, until After the construction of the selected multiple pieces of feature data is completed, multip...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an industrial control security detection method based on feature expansion. 0 The average time T of the first n pieces of data, n ≥ 4, construction time feature = data time t 0 ‑Average time T; use the constructed time feature to construct a data matrix, and use the constructed data matrix with time features as a set of data; then operate as above to construct a second set of data for the next selected feature data, until After the construction of the selected multiple pieces of feature data, multiple sets of data are obtained, and the first preprocessing step is completed; S2, the multiple sets of data obtained after the first preprocessing are input into the model for training, which is used to perform industrial control security detection after training. The present invention simplifies feature selection, forms feature enrichment, realizes multi-dimensional pre-judgment recognition, improves detection accuracy, improves training speed, and the like.
Description
technical field [0001] The invention relates to the field of industrial information security, and more specifically, to an industrial control security detection method based on feature expansion. Background technique [0002] Hacker attacks on industrial control systems are on the rise, due to the informatization and networking of industrial production. Industrial control system production continuity, equipment complexity, industry process differences, strong coupling of product components, diversity of network protocols, monopoly of manufacturing technology, indifference of personnel safety information awareness, etc., lead to difficulties in information security protection of industrial control systems. . [0003] The existing artificial intelligence-based industrial control network data detection is mainly divided into traditional machine learning detection and RNN-related and variant-based detection based on natural language framework (such as figure 1 shown), all igno...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & AuthorityPatents(China)
IPC IPC(8): G06F21/55G06N3/02G06N3/08G06N20/00
Inventor刘朝羽郭晓玲邹大均幸享宏张文科
Owner工业信息安全(四川)创新中心有限公司