Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Password strength detection method based on high-frequency character string PCFG model

A technology of strength detection and character strings, which is applied in the field of system security, can solve problems such as too fine-grained passwords, and achieve the effect of improving password security

Pending Publication Date: 2022-06-07
FUDAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The original string-based Markov model and the neural network-based FLA model basically use a character-level model, using a single character as the basic unit of a password. However, dividing passwords by characters may be too fine-grained.

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
  • Password strength detection method based on high-frequency character string PCFG model
  • Password strength detection method based on high-frequency character string PCFG model
  • Password strength detection method based on high-frequency character string PCFG model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The experiments employ a cross-site guessing scenario, where a model is trained using an old dataset (a dataset leaked in earlier years) and then applied to crack a recently leaked dataset. For foreign passwords, use Rockyou to train a model to crack Neopets and Cit0day, and for domestic passwords, use CSDN to train a model to crack youku and 178. Duplicate passwords that appear in the training set are removed from the evaluation set to demonstrate the ability of the model to generate new (or unseen) valid passwords. In addition, 10% of the passwords were randomly sampled in the evaluation set to ensure a larger training set and eliminate the effect of a small training set, since data-driven models should theoretically guarantee that the training set is larger than the evaluation set. Also, considering that using a single model may be biased, the Min_auto strategy is introduced, which shows the performance of using multiple guessing methods.

[0047] PSM framework

[...

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 belongs to the technical field of system security, and particularly relates to a password strength detection method based on a high-frequency character string PCFG model. The method comprises the following steps of: dividing a password into smaller composition units by using a special word segmentation method for the password; constructing and training a PCFG model by using the password after word segmentation; detecting the password strength by using the model and feeding back the password strength to the user to obtain graded strength information; and compressing the model and deploying the model at a browser end and a server end. According to the method, the password is automatically decomposed into high-frequency character strings by using a word segmentation method, so that the mode that the same character type is generally used for grouping the character strings at present is changed; the overestimation of a strength detection tool on the password is reduced, and an accurate password strength evaluation result is obtained; according to the method, the password strength of the user is fed back, more information is fed back to explain the weak password generation reason, and the user is informed of which high-frequency character strings adopted in the password are important factors causing formation of the weak password, so that the user can conveniently and specifically improve the password safety of the user.

Description

technical field [0001] The invention belongs to the technical field of system security, in particular to a password strength detection method based on a high-frequency character string PCFG. Background technique [0002] The PasswordStrengthMeter is used to detect the strength of a single password, and is generally deployed on clients such as websites by password administrators. A good password strength measurer can not only let users know the security level of their own passwords, but also make suggestions for users' passwords and help users correct weak passwords. However, the password strength measurers currently used by most browsers can only return the strength results of the user's password, and cannot explain the reason why the user chooses a weak password. CKL_PSM [1] The innovation of CKL_PSM is that it adopts the most efficient guessing model so far, which can feedback the password strength more accurately; secondly, CKL_PSM can not only return the password stren...

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): G06F21/46G06N20/00
CPCG06F21/46G06N20/00
Inventor 徐铭江宵汉黄一力韩伟力柴洪峰
Owner FUDAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products