Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Abnormal flow detection method based on neural network

An abnormal traffic and neural network technology, applied in the field of abnormal traffic detection, can solve problems such as unbalanced data distribution, achieve the effect of improving detection accuracy, improving model accuracy, and improving effects

Active Publication Date: 2021-07-30
HARBIN ENG UNIV
View PDF9 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a method for detecting abnormal traffic based on a neural network that solves the problem of abnormal traffic detection caused by unbalanced data distribution in the training data set and improves the performance of the detection model

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
  • Abnormal flow detection method based on neural network
  • Abnormal flow detection method based on neural network
  • Abnormal flow detection method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] 1. Combine figure 1 , the present invention proposes a method for detecting abnormal traffic based on a neural network, specifically comprising the following steps:

[0060] Step 1: Preprocess the original data set, including numericalization and normalization of the data. Numericalization is to represent discrete character variables with integer data for easy processing; normalization is to quantify The data of different classes are normalized to 0-1 to avoid the impact of the large difference in magnitude.

[0061] Step 2: Use the oversampling method to expand the minority category samples.

[0062] Step 3: Use the undersampling method to clean the samples.

[0063] Step 4: Enter the network training and get the model.

[0064] 2. The specific steps of step 2 for oversampling the minority category samples are as follows:

[0065] Step 2.1: Determine the discrete feature dc in the sample, and the expansion number t of each minority class sample.

[0066] Step 2.2:...

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 abnormal traffic detection, and particularly relates to an abnormal traffic detection method based on a neural network. The method comprises the following steps: re-sampling a traffic sample with unbalanced data through a sampling technology so as to avoid and reduce the influence of the data imbalance on detection; inputting the sample data into the network for detection, optimizing the network from two aspects of a space structure and a feature weight, and improving the structure of the network according to the characteristics of the abnormal traffic, so the network detection accuracy is improved. According to the method, resampling and the neural network are combined, the model accuracy is improved, and the abnormal flow detection effect is effectively improved. According to the method, the influence of data imbalance on a classification result can be effectively reduced, the network is optimized according to the characteristics of flow detection, and the detection accuracy is improved. According to the method, the abnormal traffic detection problem of unbalanced data distribution in the training data set is solved, and the performance of the detection model is improved.

Description

technical field [0001] The invention belongs to the technical field of abnormal traffic detection, and in particular relates to a neural network-based abnormal traffic detection method. Background technique [0002] With the increasing application of Internet technology, security issues have become a security issue that needs to be solved urgently. How to defend against external network attacks has become a key concern of relevant practitioners all over the world. Abnormal traffic detection is an important part of network security defense work. In view of the current network security problems in industrial control systems, abnormal traffic detection can be used to collect and detect the traffic in the industrial control network to discover possible attacks and make decisions. response. Abnormal traffic detection is to collect the traffic in the network and extract the useful information into features, and use the features to describe the traffic, so as to find out whether t...

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 Applications(China)
IPC IPC(8): H04L29/06G06N3/04G06N3/08
CPCH04L63/1425G06N3/08G06N3/045
Inventor 李明旭
Owner HARBIN ENG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com