Unlock instant, AI-driven research and patent intelligence for your innovation.

Method, device and system for intelligent prediction of security situation based on deep neural network

A deep neural network and security posture technology, applied in the field of network security, can solve problems such as strong dependence on label data, and achieve the effect of improving prediction ability and accuracy

Active Publication Date: 2022-04-22
PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] For this reason, the present invention provides a security situation intelligent prediction method, device and system based on a deep neural network, which solves problems such as the strong dependence of the existing network security situation on label data, improves the application of the neural network in the field of situation prediction, and has a comparative advantage. Strong practicability and operability

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method, device and system for intelligent prediction of security situation based on deep neural network
  • Method, device and system for intelligent prediction of security situation based on deep neural network
  • Method, device and system for intelligent prediction of security situation based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] To make the object, technical solution and advantages of the present invention more clear and understood, the following in conjunction with the accompanying drawings and technical solutions of the present invention will be further described in detail. The technical terms involved in the embodiment are as follows:

[0038] The neural network-based method has become one of the mainstream methods of current situation prediction because of its good self-learning ability, but it is strongly dependent on data labels. Since the training process of neural network is a supervised learning process, which is essentially the process of using data to guide the network to find the connection between features and labels and adjust to the optimal structure, a large amount of label data is required as a training set, and in the actual environment, labeled network security posture data is often scarce, which restricts the application of neural networks in the field of situation prediction an...

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

No PUM Login to View More

Abstract

The invention belongs to the technical field of network security, and in particular relates to a method, device and system for intelligent prediction of security situation based on a deep neural network. A deep self-encoding network model based on unsupervised training and learning of network security situation; combined with expert knowledge and hierarchical evaluation of deep self-encoding network model, unsupervised layer-by-layer pre-training and supervised model parameter fine-tuning are sequentially performed to obtain a trained network model; based on training After the network model, the target network security situation is predicted. The present invention solves the problem of dependence on network security data labels by using the deep self-encoder as the basic structure, adopts the unsupervised layer-by-layer algorithm for pre-training, and adopts the supervised algorithm for parameter fine-tuning, and realizes the automatic monitoring and intelligence of the security situation. Early warning to improve the accuracy and timeliness of situation forecasting.

Description

Technical field [0001] The present invention belongs to the field of network security technology, particularly relates to a security situation intelligent prediction method based on a deep neural network, apparatus and system. Background [0002] With the major breakthroughs in artificial intelligence technology with machine learning algorithms as the core and the emergence of big data analysis platform systems, the introduction of artificial intelligence technology into the situation prediction process has become a significant technological development trend. Situational prediction is a core component of situational awareness technology, focusing on how to assess and predict future trends based on current and historical information in the system. It predicts trends in future states based on information collected in the past and information about situations currently understood. Situation prediction enables decision makers to grasp the state of cyberspace more predictably and co...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06N3/08
CPCG06N3/084G06F18/214
Inventor 张玉臣胡浩张任川刘玉岭汪永伟鲍旭华孙怡峰周洪伟范钰丹何淼
Owner PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU