Verification method and device

Abstract

An embodiment of the invention provides a verification method and device. The method includes: acquiring user verification data which are generated by user behaviors; generating machine verification data through machine simulation according to the user verification data, wherein the machine verification data are used for representation of verification data generated by machine behaviors; taking the user verification data as a positive sample and the machine verification data as a negative sample to generate a user verification behavior model through machine learning, wherein the user verification behavior model is used for judging whether verification requests are user behaviors or machine behaviors.

Description

technical field [0001] The present application relates to the technical field of web page development, in particular to a verification method and device. Background technique [0002] At present, in order to increase the security of network information in the web browser interface, for example, to prevent malicious cracking of passwords, swiping tickets, flooding forums, or continuous login attempts for specific registered users using specific program brute force cracking methods, generally use Verify the information for verification. After the user enters the user name and static password, the network side will send a random verification information to the client. The user can identify the content of the verification information with the naked eye, input it into the input box of the client, and submit it to the website for verification. After success, the user can perform normal follow-up operations through the client. [0003] At present, the verification information use...

AI Technical Summary

Problems solved by technology

[0004] 1. Verification information in the form of numbers and letters: This verification information may be all letters, or all numbers, or a combination of letters and numbers, such as a randomly generated 4-digit string, which is easy to verify The information identification program is cracked, which cannot prevent malicious submissions

[0005] 2. Verification information in the form of Chinese characters: This verification information is at least one Chinese character randomly generated. This verification information can also be deciphered by the recognition program of the verification information, and the user needs to switch the input method when entering Chinese characters, which is troublesome and not conducive to users to experience

Or, distort the numbers and letters in the generated verification information picture, which is not conducive to user identification

[0007] The verification information generated by the above-mentioned existing schemes may be cracked by the identification program, and the machine cannot be filtered correctly to achieve the purpose of security authentication on the page, especially the behavior of maliciously submitting the page cannot be avoided, causing hidden dangers in network security

Images