Network threat attack feature unified quantification method based on style migration

A technology of attack characteristics and quantification methods, applied in the field of network security technology and network security threats, can solve the problems of long model training time and low training efficiency, so as to improve the network threat perception ability, overcome the problem of dimensional disaster, and improve the detection rate. Effect

Inactive Publication Date: 2020-05-12
SICHUAN UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the increasing amount of Internet data, the diversification of related network activities, and the increasingly hidden means of network threats, the current network threat detection

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
  • Network threat attack feature unified quantification method based on style migration
  • Network threat attack feature unified quantification method based on style migration
  • Network threat attack feature unified quantification method based on style migration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] The present invention designs a unified quantification method of network threat attack features based on style migration, which can automatically extract high-level features of multi-dimensional network threat data, and can also realize unified quantitative processing of multiple threat sources at the same time. In particular, the following setting method is adopted: different The original feature map of the dimension is processed uniformly, including the following steps:

[0055] 1) Data collection: real-time collection of network flow data;

[0056] 2) Select the basic features of the network flow data;

[0057] 3) Use Minkowski Distance to convert the basic features of the selected network flow into native feature maps of different dimensions;

[0058] 4) Use CNN to build a generation network, and input the "native feature map" in the data set into the "generation network" to generate a "result map";

[0059] 5) Extract the high-level features of the original featu...

Embodiment 2

[0080] This embodiment is further optimized on the basis of the above embodiments, a unified quantification method for network threat attack characteristics based on style transfer, such as figure 1 , figure 2 , image 3 shown, including the following steps:

[0081] S1. Data collection:

[0082] Through real-time collection of network flow data, such as basic security detection units such as firewalls, intrusion detection systems, vulnerability scanning systems, anti-virus systems, and terminal security management systems, as well as comprehensive network flow data such as security management platforms and security operation centers, network flow During data collection, the collection content includes packet size, duration, data packet timing, flow duration, message arrival time interval, access domain name, port, IP, URL, DNS and other information.

[0083] S2. Basic feature selection of network flow:

[0084] Select such as source IP address, destination IP address, so...

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 discloses a network threat attack feature unified quantification method based on style migration, and is used for carrying out unified processing on native feature maps of different dimensions. The method comprises the following steps: 1) data acquisition: acquiring network flow data in real time; 2) selecting basic characteristics of the network flow data; 3) converting the basic characteristics of the selected network flow into native characteristic graphs of different dimensions by using Minkowski Distance; 4) establishing a generative network by adopting a CNN, and inputtingthe "native feature map" in the data set into the "generative network" to generate a "result map"; 5) extracting high-level features of the native feature map through a loss network and making loss calculation of generated results with target "style graph" and "native feature graph" respectively; and 6) characteristic unified quantification: adjusting the weight of the generative network accordingto the loss value calculated in the step 5) so as to automatically extract the high-level characteristics of the multi-dimensional network threat data and also simultaneously realize unified quantification processing on multiple threat sources.

Description

technical field [0001] The invention relates to the fields of network security technology, network security threat technology, etc., specifically, a method for uniformly quantifying network threat attack features based on style migration. Background technique [0002] my country has become one of the countries that suffer the most serious cyber attacks in the world, and the current situation of network security is very grim. The network threat awareness system has always been the key and core technology to ensure the security of cyberspace. With the increasing amount of Internet data, the diversification of related network activities, and the increasingly hidden means of network threats, the current network threat detection methods face the problems of long model training time, low training efficiency, and insufficient training. Under the current situation, the traditional network threat detection technology has faced new challenges. [0003] Machine learning (Machine Lear...

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
IPC IPC(8): H04L29/06H04L12/24
CPCH04L41/142H04L41/145H04L63/1416
Inventor 杨进李涛梁刚赵辉高天予唐晔晨
Owner SICHUAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap