Random forest based automatic pass test method for sliding verification code

A technology of random forest and testing method, applied in digital data authentication, computer security devices, instruments, etc., can solve problems such as rejection, and achieve the effect of improving security, low cost, and efficient automation

Active Publication Date: 2018-02-23
北京知道未来信息技术有限公司
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it also reflects that the security performance of the sliding verification code is still very high. Basically, the robot can be recognized and rejected.

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
  • Random forest based automatic pass test method for sliding verification code
  • Random forest based automatic pass test method for sliding verification code

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to make the above-mentioned features and advantages of the present invention more comprehensible, the following specific embodiments are described in detail in conjunction with the accompanying drawings.

[0046] Firstly, determine the parameters required for sliding verification code verification, and then determine the generation rules of these parameters. This step needs to be debugged through firebug or other debugging tools. These dimensions that affect verification code verification generally include trajectory, passing time, request number, picture number, etc. Of course, there are some request verification, such as cookie, user_agent, js loading time, etc.

[0047] Most dimensions can be passed in a fixed mode, such as by requesting the authentication number obtained from the server. This number may be encrypted to obtain the final output parameter. You can find the encryption function through debugging, and then re-execute the encryption function to g...

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 random forest based automatic pass test method for a sliding verification code. The method comprises the steps that according to an encrypted field in the sliding verification code, a locus encryption function and locus parameters are obtained; locus parameter values are collected, reverse inverse solution is conducted on the locus parameter values according to the encryption function, and an obtained original array generates training data; the training data is subjected to regression training with a random forest, a locus module is obtained, and normalization processing is conducted; multiple data points of different times of different normalized loci are obtained multiple times in a random mode, data points selected each time are subjected to fitting on the samenumber axis, and an optimal fitting locus is selected from multiple obtained fitting loci; a picture of the sliding verification code is obtained, missing piece shadow position information is input into the optimal fitting locus, a pass locus is obtained, and a simulated web page request is generated and sent to a server. Accordingly, machine automation can be achieved efficiently through the sliding verification code, and great convenience is brought to a tester.

Description

technical field [0001] The invention belongs to the technical field of computer software, and relates to an automatic pass test method of a random forest-based sliding verification code. Background technique [0002] Random forest (random forest) is an integrated algorithm based on a decision tree-based learner. The random forest is composed of multiple decision trees, and each tree in the forest does not affect each other. The final result of the model consists of multiple decision trees. The tree decides. When dealing with classification problems, each tree will criticize a final category, and then the output category will be decided by voting, and the minority obeys the majority. When dealing with regression problems, the mean output of each decision tree is used as the final result. [0003] Most of the existing interactive sliding verification code passing methods first use js to record the user's mouse movement trajectory, and then continuously collect different loca...

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): G06F21/31G06F21/46
CPCG06F21/316G06F21/46
Inventor 姚森友
Owner 北京知道未来信息技术有限公司
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