Application layer malicious request detection method based on Transformer model

A detection method and application layer technology, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve the problems of improving the effectiveness and efficiency of malicious traffic detection methods

Active Publication Date: 2019-10-22
长沙市智为信息技术有限公司
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the effect and efficiency of the current application-layer malicious

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
  • Application layer malicious request detection method based on Transformer model
  • Application layer malicious request detection method based on Transformer model
  • Application layer malicious request detection method based on Transformer model

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0039] The specific implementation method of the inventive method is as follows:

[0040] Step 1. The process of data acquisition. First, the application layer user request data recorded by the application service is obtained to form the application layer user request data set R, in which each application layer user request data R i The included features include request header and request body, the request header contains the data attribute information requested by the user, and the request body contains the data content information requested by the user; then according to a single application layer user request data R i , according to manual detection or other feasible detection methods, get its real category label vector L i , where the first element value represents R i is the probability value of a normal request, and the second element value represents R i is the probability value of a malicious request, L i The value of (0, 1) or (1, 0), (0, 1) represents R...

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 provides an application layer malicious request detection method based on a Transformer model. The method comprises the following steps: firstly, constructing an application layer user request data sample set; constructing a dictionary according to the occurrence frequency of lexical elements in the application layer user request data, and vectorizing the application layer user request data according to the dictionary; performing data embedding and position encoding on a vectorized result to obtain a feature matrix; predicting the category of the user request data of the corresponding application layer for the feature matrix based on a Transformer model; calculating a loss function value according to a model prediction category and a real category, and optimizing network parameters; and finally, vectorizing to-be-detected application layer user request data, and performing feature extraction and category prediction on the to-be-detected application layer user request databased on the optimized network to realize application layer malicious request detection. The method is good in effect and high in efficiency.

Description

technical field [0001] The invention belongs to the technical field of computer information processing, and relates to a Transformer model-based application layer malicious request detection method. Background technique [0002] Application services are the main way for application service providers to provide services for users (such as e-commerce websites), and are closely related to our real life. However, criminals often attack by constructing malicious requests at the application layer to seek illegitimate benefits. The traditional application layer malicious request detection method uses pattern matching with security protection rules written by security practitioners. This method has problems such as huge rule base, difficult maintenance, and poor universality. [0003] In recent years, with the rapid development of artificial intelligence, researchers have begun to use deep learning methods for the detection of malicious traffic at the application layer. This metho...

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): G06F21/56G06K9/62G06N3/08
CPCG06F21/561G06N3/08G06F18/24
Inventor 马小龙赵颖谢逸航曹鸣佩黄惟康占英陈文江
Owner 长沙市智为信息技术有限公司
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