Supercharge Your Innovation With Domain-Expert AI Agents!

Malicious Traffic Detection Method Fused with Deep Neural Network and Hierarchical Attention Mechanism

A detection method, malicious traffic technology, applied in neural learning methods, biological neural network models, neural architectures, etc.

Active Publication Date: 2021-11-23
芽米科技(广州)有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But because the machine learning algorithm can only be used as a classifier, it has many limitations, and when the intrusion becomes more and more complex and diverse

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
  • Malicious Traffic Detection Method Fused with Deep Neural Network and Hierarchical Attention Mechanism
  • Malicious Traffic Detection Method Fused with Deep Neural Network and Hierarchical Attention Mechanism
  • Malicious Traffic Detection Method Fused with Deep Neural Network and Hierarchical Attention Mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0114] Embodiments of the present invention will be described in detail below, and examples of the embodiments are illustrated in the drawings, in which the same or similar reference numerals represent the same or similar elements or elements having the same or similar functions. The following is exemplary, and is intended to be illustrative of the invention, not to be construed as limiting the invention.

[0115] The present invention proposes a hierarchical precaution model (HAGRU) for malicious flow detection, and the model is based on currently effective, reliable depth cycle neural network. The hierarchical attention is compared with the previously proposed neural network for malicious flow detection, a relatively high detection rate, a relatively low false positive rate and relatively good real-time. Schematic diagram of the hierarchical attention of malicious flow detection figure 1 Indicated.

[0116] The hierarchical precision model (HAGRU) designed for malicious flow det...

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 present invention proposes a malicious traffic detection method that integrates a deep neural network and a hierarchical attention mechanism, including the following steps: S1, obtaining original traffic data, and saving the acquired original traffic data as traffic data in an identifiable file format ; S2, performing feature conversion on the traffic data saved in step S1; S3, performing data packet segmentation on the converted traffic data in step S2, to obtain data packet segments; S4, capturing each data packet segment through time series processing feature vector The feature information between them; S5, allocate attention vectors; S6, perform feature fusion on the flow data; S7, perform linear transformation on the features fused in step S6; S8, classify the flow data. The invention can detect malicious traffic and enhance performance.

Description

Technical field [0001] The present invention relates to a method of detecting malicious flow technologies, and more particularly to a malicious flow detection method for fusion depth neural network and hierarchical attention. Background technique [0002] With the continuous development of computer networks, it is constantly changing people's lives, learning, and working methods, but is currently facing a variety of security threats, and this threat has become more serious. It has soon proposed a network security, which includes strategies and practices that prevent and monitor computer networks and access to resources through the network access resources. Network security mainly includes the confidentiality, integrity and availability of its carrier information (CONFIDENTIAL INTEGRITY AVAILITY, CIA). Any activity that tries to destroy CIA or bypass the setting network security mechanism can be considered network invasion. At present, security fields generally adopt intrusion det...

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): H04L29/06G06K9/62G06N3/04G06N3/08
CPCH04L63/1416H04L63/1425G06N3/084G06N3/045G06F18/2415G06F18/253
Inventor 刘小洋刘加苗丁楠
Owner 芽米科技(广州)有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com