A password attack evaluation method based on conditional variational self-coding

Abstract

The invention provides a password attack evaluation method based on conditional variational self-coding. The method comprises the following steps of constructing a variational self-coding model, constructing a conditional variational self-coding model, constructing a password attack model, and comprehensively utilizing the conditional variational self-coding model and the password attack model. According to the invention, a conditional variational self-coding model, and the condition characteristics in the personal information of the user, such as the user name, the mailbox address, the telephone number, etc. are used to train the cryptographic attack model, a bidirectional GRU recurrent neural network and a CNN text convolutional neural network are respectively used at the encoder end, sothat the code of a password sequence and personal information of a user and abstract extraction of characteristics can be achieved, the distribution of password data and a character combination rulecan be effectively fitted, the high-quality guessing password data can be generated, and the method has a remarkable effect on improving the password strength and safety of the user.

Description

technical field [0001] The invention relates to the field of Internet data encryption, in particular to a cryptographic attack evaluation method based on conditional variational self-encoding. Background technique [0002] Variational Autoencoder (VAE) is a generative model based on a regularized version of the standard autoencoder model. [0003] Passwords are a common way of data encryption and user authentication. The passwords set by users are not completely random, so they are vulnerable to password cracking tools. Using a password guessing algorithm is an effective way to assess the strength and security of a user's password. [0004] However, user passwords are prone to some disadvantages. Multiple password database leaks indicate that users tend to choose passwords that are easy to guess, mainly composed of common strings and numbers, and many password creation rules contain a variety of personal information combinations Therefore, it is easy to be attacked by pass...

AI Technical Summary

Problems solved by technology

[0004] However, user passwords are prone to some disadvantages. Multiple password database leaks indicate that users tend to choose passwords that are easy to guess, mainly composed of common strings and numbers, and many password creation rules contain a variety of personal information combinations Therefore, it is easy to be attacked by password deciphering algorithms. It is a very important security issue to confirm whether the user's password setting is safe; some existing traditional statistical methods cannot accurately learn the user's password setting habits, and at the same time need to consume a lot of calculations Resource and time costs are not suitable for real-time password strength assessment, and most of the existing password security detection algorithms only consider the probability distribution of characters in the password data set, and do not include user personal information (such as email address, user name, etc.) ) into feature conditions, and these personal information often have a strong correlation with passwords

Images