CN113254905A - Password dictionary fusion method and system based on probability weight - Google Patents
Password dictionary fusion method and system based on probability weight Download PDFInfo
- Publication number
- CN113254905A CN113254905A CN202110774952.9A CN202110774952A CN113254905A CN 113254905 A CN113254905 A CN 113254905A CN 202110774952 A CN202110774952 A CN 202110774952A CN 113254905 A CN113254905 A CN 113254905A
- Authority
- CN
- China
- Prior art keywords
- password
- merged
- dictionary
- candidate
- repeated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/237—Lexical tools
- G06F40/242—Dictionaries
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/20—Network architectures or network communication protocols for network security for managing network security; network security policies in general
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/32—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials
- H04L9/3226—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols including means for verifying the identity or authority of a user of the system or for message authentication, e.g. authorization, entity authentication, data integrity or data verification, non-repudiation, key authentication or verification of credentials using a predetermined code, e.g. password, passphrase or PIN
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computer Hardware Design (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Storage Device Security (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a password dictionary fusion method based on probability weight, which comprises the following steps: all the password dictionaries to be combined are obtained, and hit rate testing is carried out on each password dictionary to be combined; after repeating candidate password statistics is carried out on all the password dictionaries to be combined, combining the password dictionaries to be combined corresponding to the repeated candidate passwords; calculating the weight of each repeated candidate password in each password dictionary to be combined in the corresponding password dictionary set to be combined; acquiring a sequence value of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged; calculating a fused sequence value of each repeated candidate password; and sequencing the fusion sequence values of all the repeated candidate passwords to generate a password fusion dictionary. The invention also provides a password dictionary fusion system based on the probability weight. The method and the device can improve the hit rate of password guessing, adapt to various password guessing scenes such as online and offline and directional walking, and further more accurately evaluate the strength of password anti-guessing.
Description
Technical Field
The invention belongs to the field of password security evaluation, and particularly relates to a probability weight-based password dictionary fusion method and system.
Background
The internet has profoundly changed the production and living modes of people, and the network space has become the fifth territory affecting the national security. With the continuous networking of people's daily life, the assets are continuously digitalized, and identity authentication gradually becomes the basic means for guaranteeing user information safety. Password authentication is the most common technology of network identity authentication at present, and has important research value in the field of network security.
One important direction in password security research is password guessing. Researchers can explore from the perspective of attackers, and research how to use a probability algorithm to guess exit commands more efficiently through large-scale password data mining, so as to evaluate the strength of self-guessing of passwords. With the intensive research on password guessing technology, a plurality of more typical password guessing probability algorithms, such as N-order Markov (Markov N-grams) and probability Context-Free semantics (PCFG), have appeared in succession, and the proposal of these probability algorithms introduces the password guessing technology research into a scientific orbit supported by a strict theoretical system. It has been found that each probabilistic algorithm has its unique advantages in password guessing. The password guessing model based on the Markov algorithm considers the relevance among characters of the user password, ignores the semantic thinking of the user, is suitable for a scene of offline walk guessing, and has low hit rate on a scene of online directional guessing (namely limiting the number of times of password guessing). A password guessing model based on a PCFG algorithm generates an input password into a composition structure according to the meaning, the semantic habit followed by the password set by a user is analyzed, but the relevance between the front character and the rear character existing in the password is ignored, and the password guessing model is suitable for a scene of on-line directional guessing, but cannot generate enough guessed passwords and is not suitable for a scene of off-line walking guessing.
Disclosure of Invention
One of the objectives of the present invention is to provide a password dictionary fusion method based on probability weight, which can improve the hit rate of password guessing as a whole, and adapt to various password guessing scenarios such as online-offline and directional roaming, so as to more accurately evaluate the strength of password anti-guessing.
The second objective of the present invention is to provide a password dictionary fusion system based on probability weight.
In order to achieve one of the purposes, the invention adopts the following technical scheme:
a password dictionary fusion method based on probability weight comprises the following steps:
step one, all the password dictionaries to be combined are obtained, and hit rate testing is carried out on each password dictionary to be combined to obtain the hit rate of each password dictionary to be combined;
step two, carrying out repeated candidate password statistics on all the password dictionaries to be combined to obtain a password dictionary to be combined corresponding to each repeated candidate password, and combining the password dictionaries to be combined into a password dictionary set to be combined corresponding to the repeated candidate passwords;
step three, calculating the weight of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary to be merged set according to the hit rate of each password dictionary to be merged in each password dictionary to be merged set;
acquiring sequence values of the repeated candidate passwords in the password dictionaries to be merged in the corresponding password dictionary sets to be merged;
step five, calculating a fusion sequence value of each repeated candidate password according to the weight and the corresponding sequence value of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged;
and step six, sequencing the fusion sequence values of all the repeated candidate passwords to generate a password fusion dictionary.
Further, the specific implementation process of the step two is as follows:
step 21, marking the serial number of each candidate password in each password dictionary to be merged correspondingly;
step 22, forming a candidate password set by all the marked candidate passwords and sequencing the candidate passwords according to the candidate password text;
step 23, counting each password dictionary to be merged corresponding to each repeated candidate password from the sorted candidate password set;
and 24, forming a password dictionary set to be merged corresponding to the repeated candidate passwords by using each password dictionary to be merged corresponding to each repeated candidate password.
Further, in step three, the weight of each repeated candidate password in each to-be-merged password dictionary in the corresponding to-be-merged password dictionary set is as follows:
w i k ,=pr(m i k,)/pr(m k ) ;
wherein the content of the first and second substances,w i k,is as followskThe repeated candidate passwords are in the corresponding password dictionary set to be mergediWeights in a password dictionary to be merged;pr(m i k,) Is as followskThe repeated candidate passwords are in the corresponding password dictionary set to be mergediHit rate of each to-be-merged password dictionary;pr(m k ) Is as followskThe hit rate of all the repeated candidate passwords in the corresponding password dictionary set to be merged is the sum of the hit rates of all the password dictionaries to be merged.
Further, in step five, the fused sequence value of each repeated candidate password is:
wherein the content of the first and second substances,f k is as followskA fused sequence value of a number of repeated candidate passwords;w i k,andδ i k,are respectively the firstkThe repeated candidate passwords are in the corresponding password dictionary set to be mergediWeights and sequence values in the password dictionary to be combined;i=1,2,…,n',n'is as followskThe number of the repeated candidate passwords in the corresponding password dictionary set to be merged.
Further, in step three, the weight of each repeated candidate password in each to-be-merged password dictionary in the to-be-merged password dictionary set is:
w i k ,=1-pr(m i k,);
wherein the content of the first and second substances,w i k,is as followskThe repeated candidate passwords are in the corresponding password dictionary set to be mergediWeights in a password dictionary to be merged;pr(m i k,) Is as followskIn the dictionary set of repeated candidate passwordsiHit rate of each to-be-merged password dictionary.
Further, in step five, the fused sequence value of each repeated candidate password is:
wherein the content of the first and second substances,f k is as followskA fused sequence value of a number of repeated candidate passwords;w i k,andδ i k,are respectively the firstkThe repeated candidate passwords are in the corresponding password dictionary set to be mergediWeights and sequence values in the password dictionary to be combined;i=1,2,…,n',n'is as followskThe number of the repeated candidate passwords in the corresponding password dictionary set to be merged.
In order to achieve the second purpose, the invention adopts the following technical scheme:
a probability weight-based password dictionary fusion system, the password dictionary fusion system comprising:
the acquisition module is used for acquiring all the password dictionaries to be combined and performing hit rate test on each password dictionary to be combined to obtain the hit rate of each password dictionary to be combined;
the statistic module is used for carrying out repeated candidate password statistics on all the password dictionaries to be merged to obtain a password dictionary to be merged corresponding to each repeated candidate password and then merging the password dictionaries to be merged into a password dictionary set to be merged corresponding to the repeated candidate passwords;
the first calculation module is used for calculating the weight of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged according to the hit rate of each password dictionary to be merged in each password dictionary set to be merged;
the second acquisition module is used for acquiring the sequence value of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged;
the second calculation module is used for calculating a fusion sequence value of each repeated candidate password according to the weight of each repeated candidate password in each password dictionary to be combined in the corresponding password dictionary set to be combined and the corresponding sequence value;
and the sequencing module is used for sequencing the fusion sequence values of all the repeated candidate passwords and then generating a password fusion dictionary.
Further, the statistic module comprises:
the marking submodule is used for marking the serial number of each candidate password in each password dictionary to be merged correspondingly;
the ordering submodule is used for forming a candidate password set by all the marked candidate passwords and ordering the candidate passwords according to the candidate password text;
the acquisition submodule is used for counting a password dictionary to be merged corresponding to each repeated candidate password from the ordered candidate password set;
and the merging submodule is used for enabling each password dictionary to be merged corresponding to each repeated candidate password to form a password dictionary set to be merged corresponding to the repeated candidate password.
The invention has the beneficial effects that:
the method comprises the steps of obtaining a password dictionary set to be combined of each repeated candidate password by counting a password dictionary to be combined corresponding to each repeated candidate password in all password dictionaries to be combined; calculating the weight of each repeated candidate password in each password dictionary to be combined in the corresponding password dictionary set to be combined; simultaneously acquiring sequence values of the repeated candidate passwords in the password dictionary set to be combined corresponding to the repeated candidate passwords; calculating a fusion sequence value of each repeated candidate password according to the weight and the corresponding sequence value of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged; the method has the advantages that the fusion sequence values of all repeated candidate passwords are sequenced to generate the password fusion dictionary, the password fusion dictionary is used for password guessing, the hit rate is improved compared with the original password dictionary to be combined, various password guessing scenes such as online and offline and directional walking are adapted, and the strength of password anti-guessing is evaluated more accurately.
Drawings
FIG. 1 is a flowchart illustrating a password dictionary fusion method based on probability weight according to the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings.
The embodiment provides a password dictionary fusion method based on probability weight, and referring to fig. 1, the password dictionary fusion method includes the following steps:
s1, all the password dictionaries to be combined are obtained, and hit rate testing is carried out on each password dictionary to be combined, so that the hit rate of each password dictionary to be combined is obtained.
In the embodiment, the fusion problem of a plurality of password guessing technologies is expressed as a top-K combined password dictionary generated by the combined password guessing technology, and the specific operation flow of each password guessing technology can be not considered. The embodiment calculates the statistical probability of the hit passwords of the top-K combined password dictionaries, namely the hit rate, by using the test password data.
And S2, performing repeated candidate password statistics on all the password dictionaries to be merged to obtain the password dictionary to be merged corresponding to each repeated candidate password, and merging the password dictionaries to be merged into a password dictionary set to be merged corresponding to the repeated candidate passwords.
The to-be-merged password dictionary set in this embodiment may be implemented by the prior art, or may be implemented by the following method, and the specific implementation process is as follows:
step 21, marking the serial number of each candidate password in each password dictionary to be merged correspondingly;
step 22, forming a candidate password set by all the marked candidate passwords and sequencing the candidate passwords according to the candidate password text;
step 23, counting each password dictionary to be merged corresponding to each repeated candidate password from the sorted candidate password set;
and 24, forming a password dictionary set to be merged corresponding to the repeated candidate passwords by using each password dictionary to be merged corresponding to each repeated candidate password.
S3, calculating the weight of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary to be merged according to the hit rate of each password dictionary to be merged in each password dictionary to be merged.
In this embodiment, the following 2 formulas may be adopted to calculate the weight of each repeated candidate password in each to-be-merged password dictionary in the corresponding to-be-merged password dictionary set:
the first formula:
w i k ,=pr(m i k,)/pr(m k ) ; (1)
wherein the content of the first and second substances,w i k,is as followskMultiple repeated candidate passwords in corresponding password to be mergedClassics is centered on the firstiWeights in a password dictionary to be merged;pr(m i k,) Is as followskThe repeated candidate passwords are in the corresponding password dictionary set to be mergediHit rate of each to-be-merged password dictionary;pr(m k ) Is as followskThe hit rate of all the repeated candidate passwords in the corresponding password dictionary set to be merged is the sum of the hit rates of all the password dictionaries to be merged.
The second formula:
w i k ,=1-pr(m i k,); (2)
wherein the content of the first and second substances,w i k,is as followskThe repeated candidate passwords are in the corresponding password dictionary set to be mergediWeights in a password dictionary to be merged;pr(m i k,) Is as followskIn the dictionary set of repeated candidate passwordsiHit rate of each to-be-merged password dictionary.
S4, obtaining the sequence value of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged.
S5, calculating the fusion sequence value of each repeated candidate password according to the weight and the corresponding sequence value of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged.
And aiming at the first formula (1) in the step three, obtaining the weight of each repeated candidate password in each password dictionary to be combined in the corresponding password dictionary set to be combined, and calculating the fusion sequence value of each repeated candidate password by adopting the following weighted summation formula:
wherein the content of the first and second substances,f k is as followskA fused sequence value of a number of repeated candidate passwords;w i k,andδ i k,are respectively the firstkOne repeated candidate passwordIn the corresponding to-be-merged password dictionary setiWeights and sequence values in the password dictionary to be combined;i=1,2,…,n',n'is as followskThe number of the repeated candidate passwords in the corresponding password dictionary set to be merged.
When several repeated candidate passwords respectively appear in only one password dictionary to be merged, and the fusion sequence values of the corresponding repeated candidate passwords obtained by adopting the formula (3) are the same, the repeated candidate passwords appearing in the password dictionary to be merged with high hit rate are put in front.
And aiming at the second formula (2) in the step three, obtaining the weight of each repeated candidate password in each password dictionary to be combined in the corresponding password dictionary set to be combined, and calculating the fusion sequence value of each repeated candidate password by adopting the following formula of weighting and averaging:
wherein the content of the first and second substances,f k is as followskA fused sequence value of a number of repeated candidate passwords;w i k,andδ i k,are respectively the firstkThe repeated candidate passwords are in the corresponding password dictionary set to be mergediWeights and sequence values in the password dictionary to be combined;i=1,2,…,n',n'is as followskThe number of the repeated candidate passwords in the corresponding password dictionary set to be merged.
And S6, sequencing the fusion sequence values of all the repeated candidate passwords to generate a password fusion dictionary.
The following describes the implementation process of the technical solution of this embodiment by using specific examples:
guessing algorithm for Markov passwordM 1Guessing algorithm with PCFG passwordM 2Generating top-10 candidate password dictionary respectively based on specific password training setL 1AndL 2matching a test set of particular passwords yields a top-10 candidate password dictionaryL 1AndL 2finally, a password fusion dictionary is obtained by the method of the embodiment, as shown in table 1:
TABLE 1 top-10 candidate password dictionaryL1 andL2 and password fusion dictionary
In the embodiment, a password dictionary set to be merged of each repeated candidate password is obtained by counting the password dictionaries to be merged corresponding to each repeated candidate password in all the password dictionaries to be merged; calculating the weight of each repeated candidate password in each password dictionary to be combined in the corresponding password dictionary set to be combined; simultaneously acquiring sequence values of the repeated candidate passwords in the password dictionary set to be combined corresponding to the repeated candidate passwords; calculating a fusion sequence value of each repeated candidate password according to the weight and the corresponding sequence value of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged; the method has the advantages that the fusion sequence values of all repeated candidate passwords are sequenced to generate the password fusion dictionary, the password fusion dictionary is used for password guessing, hit rate is high, various password guessing scenes such as online and offline and directional walking are adapted, and therefore strength of password anti-guessing is evaluated more accurately.
The above embodiment can be realized by the technical solutions given in the following embodiments:
yet another embodiment provides a password dictionary fusion system based on probability weights, the password dictionary fusion system comprising:
the acquisition module is used for acquiring all the password dictionaries to be combined and performing hit rate test on each password dictionary to be combined to obtain the hit rate of each password dictionary to be combined;
and the counting module is used for carrying out repeated candidate password counting on all the password dictionaries to be combined to obtain the password dictionary to be combined corresponding to each repeated candidate password and then combining the password dictionaries to be combined into the password dictionary set to be combined corresponding to the repeated candidate passwords. The statistic module comprises:
the marking submodule is used for marking the serial number of each candidate password in each password dictionary to be merged correspondingly;
the ordering submodule is used for forming a candidate password set by all the marked candidate passwords and ordering the candidate passwords according to the candidate password text;
the acquisition submodule is used for counting a password dictionary to be merged corresponding to each repeated candidate password from the ordered candidate password set;
and the merging submodule is used for enabling each password dictionary to be merged corresponding to each repeated candidate password to form a password dictionary set to be merged corresponding to the repeated candidate password.
The first calculation module is used for calculating the weight of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged according to the hit rate of each password dictionary to be merged in each password dictionary set to be merged;
the second acquisition module is used for acquiring the sequence value of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged;
the second calculation module is used for calculating a fusion sequence value of each repeated candidate password according to the weight of each repeated candidate password in each password dictionary to be combined in the corresponding password dictionary set to be combined and the corresponding sequence value;
and the sequencing module is used for sequencing the fusion sequence values of all the repeated candidate passwords and then generating a password fusion dictionary.
Although the embodiments of the present invention have been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the spirit and scope of the embodiments of the present invention.
Claims (8)
1. A password dictionary fusion method based on probability weight is characterized by comprising the following steps:
step one, all the password dictionaries to be combined are obtained, and hit rate testing is carried out on each password dictionary to be combined to obtain the hit rate of each password dictionary to be combined;
step two, carrying out repeated candidate password statistics on all the password dictionaries to be combined to obtain a password dictionary to be combined corresponding to each repeated candidate password, and combining the password dictionaries to be combined into a password dictionary set to be combined corresponding to the repeated candidate passwords;
step three, calculating the weight of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary to be merged set according to the hit rate of each password dictionary to be merged in each password dictionary to be merged set;
acquiring sequence values of the repeated candidate passwords in the password dictionaries to be merged in the corresponding password dictionary sets to be merged;
step five, calculating a fusion sequence value of each repeated candidate password according to the weight and the corresponding sequence value of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged;
and step six, sequencing the fusion sequence values of all the repeated candidate passwords to generate a password fusion dictionary.
2. The password dictionary fusion method according to claim 1, wherein the concrete implementation process of the second step is as follows:
step 21, marking the serial number of each candidate password in each password dictionary to be merged correspondingly;
step 22, forming a candidate password set by all the marked candidate passwords and sequencing the candidate passwords according to the candidate password text;
step 23, counting each password dictionary to be merged corresponding to each repeated candidate password from the sorted candidate password set;
and 24, forming a password dictionary set to be merged corresponding to the repeated candidate passwords by using each password dictionary to be merged corresponding to each repeated candidate password.
3. The password dictionary fusion method according to claim 1 or 2, wherein in step three, the weight of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged is:
w i k ,=pr(m i k,)/pr(m k ) ;
wherein the content of the first and second substances,w i k,is as followskThe repeated candidate passwords are in the corresponding password dictionary set to be mergediWeights in a password dictionary to be merged;pr(m i k,) Is as followskThe repeated candidate passwords are in the corresponding password dictionary set to be mergediHit rate of each to-be-merged password dictionary;pr(m k ) Is as followskThe hit rate of all the repeated candidate passwords in the corresponding password dictionary set to be merged is the sum of the hit rates of all the password dictionaries to be merged.
4. The password dictionary fusion method according to claim 3, wherein in step five, the fusion sequence value of each repeated candidate password is:
wherein the content of the first and second substances,f k is as followskA fused sequence value of a number of repeated candidate passwords;w i k,andδ i k,are respectively the firstkThe repeated candidate passwords are in the corresponding password dictionary set to be mergediWeights and sequence values in the password dictionary to be combined;i=1,2,…,n',n'is as followskThe number of the repeated candidate passwords in the corresponding password dictionary set to be merged.
5. The password dictionary fusion method according to claim 1 or 2, wherein in step three, the weight of each repeated candidate password in each password dictionary to be merged in the password dictionary set to be merged is:
w i k ,=1-pr(m i k,);
wherein the content of the first and second substances,w i k,is as followskThe repeated candidate passwords are in the corresponding password dictionary set to be mergediWeights in a password dictionary to be merged;pr(m i k,) Is as followskIn the dictionary set of repeated candidate passwordsiHit rate of each to-be-merged password dictionary.
6. The password dictionary fusion method according to claim 5, wherein in step five, the fusion sequence value of each repeated candidate password is:
wherein the content of the first and second substances,f k is as followskA fused sequence value of a number of repeated candidate passwords;w i k,andδ i k,are respectively the firstkThe repeated candidate passwords are in the corresponding password dictionary set to be mergediWeights and sequence values in the password dictionary to be combined;i=1,2,…,n',n'is as followskThe number of the repeated candidate passwords in the corresponding password dictionary set to be merged.
7. A password dictionary fusion system based on probability weights, the password dictionary fusion system comprising:
the acquisition module is used for acquiring all the password dictionaries to be combined and performing hit rate test on each password dictionary to be combined to obtain the hit rate of each password dictionary to be combined;
the statistic module is used for carrying out repeated candidate password statistics on all the password dictionaries to be merged to obtain a password dictionary to be merged corresponding to each repeated candidate password and then merging the password dictionaries to be merged into a password dictionary set to be merged corresponding to the repeated candidate passwords;
the first calculation module is used for calculating the weight of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged according to the hit rate of each password dictionary to be merged in each password dictionary set to be merged;
the second acquisition module is used for acquiring the sequence value of each repeated candidate password in each password dictionary to be merged in the corresponding password dictionary set to be merged;
the second calculation module is used for calculating a fusion sequence value of each repeated candidate password according to the weight of each repeated candidate password in each password dictionary to be combined in the corresponding password dictionary set to be combined and the corresponding sequence value;
and the sequencing module is used for sequencing the fusion sequence values of all the repeated candidate passwords and then generating a password fusion dictionary.
8. The password dictionary fusion system of claim 7, wherein the statistics module comprises:
the marking submodule is used for marking the serial number of each candidate password in each password dictionary to be merged correspondingly;
the ordering submodule is used for forming a candidate password set by all the marked candidate passwords and ordering the candidate passwords according to the candidate password text;
the acquisition submodule is used for counting a password dictionary to be merged corresponding to each repeated candidate password from the ordered candidate password set;
and the merging submodule is used for enabling each password dictionary to be merged corresponding to each repeated candidate password to form a password dictionary set to be merged corresponding to the repeated candidate password.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110774952.9A CN113254905B (en) | 2021-07-09 | 2021-07-09 | Password dictionary fusion method and system based on probability weight |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110774952.9A CN113254905B (en) | 2021-07-09 | 2021-07-09 | Password dictionary fusion method and system based on probability weight |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113254905A true CN113254905A (en) | 2021-08-13 |
CN113254905B CN113254905B (en) | 2021-09-24 |
Family
ID=77191163
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110774952.9A Active CN113254905B (en) | 2021-07-09 | 2021-07-09 | Password dictionary fusion method and system based on probability weight |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113254905B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120284783A1 (en) * | 2011-06-01 | 2012-11-08 | Ebay, Inc. | Password check by decomposing password |
CN108111310A (en) * | 2017-03-09 | 2018-06-01 | 张长富 | A kind of generation method and device of candidate password dictionary |
CN108229138A (en) * | 2018-01-11 | 2018-06-29 | 浙江九州量子信息技术股份有限公司 | A kind of password dictionary generation method based on deep learning algorithm |
CN108763920A (en) * | 2018-05-23 | 2018-11-06 | 四川大学 | A kind of password strength assessment model based on integrated study |
CN109558723A (en) * | 2018-12-06 | 2019-04-02 | 南京中孚信息技术有限公司 | Password dictionary generation method, device and computer equipment |
CN109635530A (en) * | 2018-11-16 | 2019-04-16 | 华东师范大学 | A kind of intelligent password guess method based on groups of users attribute |
CN110708169A (en) * | 2019-10-19 | 2020-01-17 | 潘安琪 | Password attack method based on structure division |
CN112257433A (en) * | 2020-12-23 | 2021-01-22 | 四川大学 | Password dictionary generation method and system based on Markov chain and neural network |
CN112632526A (en) * | 2021-01-07 | 2021-04-09 | 复旦大学 | User password modeling and strength evaluation method based on comprehensive segmentation |
CN112861113A (en) * | 2021-01-08 | 2021-05-28 | 复旦大学 | Password guessing method of parameterized hybrid model |
CN113051873A (en) * | 2021-03-22 | 2021-06-29 | 中国人民解放军战略支援部队信息工程大学 | Lightweight password guessing dictionary generation method and device based on variational self-encoder |
-
2021
- 2021-07-09 CN CN202110774952.9A patent/CN113254905B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120284783A1 (en) * | 2011-06-01 | 2012-11-08 | Ebay, Inc. | Password check by decomposing password |
CN108111310A (en) * | 2017-03-09 | 2018-06-01 | 张长富 | A kind of generation method and device of candidate password dictionary |
CN108229138A (en) * | 2018-01-11 | 2018-06-29 | 浙江九州量子信息技术股份有限公司 | A kind of password dictionary generation method based on deep learning algorithm |
CN108763920A (en) * | 2018-05-23 | 2018-11-06 | 四川大学 | A kind of password strength assessment model based on integrated study |
CN109635530A (en) * | 2018-11-16 | 2019-04-16 | 华东师范大学 | A kind of intelligent password guess method based on groups of users attribute |
CN109558723A (en) * | 2018-12-06 | 2019-04-02 | 南京中孚信息技术有限公司 | Password dictionary generation method, device and computer equipment |
CN110708169A (en) * | 2019-10-19 | 2020-01-17 | 潘安琪 | Password attack method based on structure division |
CN112257433A (en) * | 2020-12-23 | 2021-01-22 | 四川大学 | Password dictionary generation method and system based on Markov chain and neural network |
CN112632526A (en) * | 2021-01-07 | 2021-04-09 | 复旦大学 | User password modeling and strength evaluation method based on comprehensive segmentation |
CN112861113A (en) * | 2021-01-08 | 2021-05-28 | 复旦大学 | Password guessing method of parameterized hybrid model |
CN113051873A (en) * | 2021-03-22 | 2021-06-29 | 中国人民解放军战略支援部队信息工程大学 | Lightweight password guessing dictionary generation method and device based on variational self-encoder |
Non-Patent Citations (1)
Title |
---|
谢志杰 等: "基于攻击算法的海量真实用户口令数据分析", 《计算机科学》 * |
Also Published As
Publication number | Publication date |
---|---|
CN113254905B (en) | 2021-09-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Hsu et al. | Learning-Based Frequency Estimation Algorithms. | |
Lin et al. | Filter sketch for network pruning | |
CN107368752B (en) | A kind of depth difference method for secret protection based on production confrontation network | |
CN106980648B (en) | Personalized recommendation method based on probability matrix decomposition and combined with similarity | |
CN107038480A (en) | A kind of text sentiment classification method based on convolutional neural networks | |
Niu et al. | Federated learning for face recognition with gradient correction | |
CN108520213A (en) | A kind of face beauty prediction technique based on multiple dimensioned depth | |
CN104794222B (en) | Network form semanteme restoration methods | |
CN110110663A (en) | A kind of age recognition methods and system based on face character | |
CN110705343A (en) | Face recognition method and system for structure-incoherent projection dictionary pair learning | |
CN109949174A (en) | A kind of isomery social network user entity anchor chain connects recognition methods | |
CN110708169A (en) | Password attack method based on structure division | |
CN109948242A (en) | Network representation learning method based on feature Hash | |
Wu et al. | Densely Supervised Hierarchical Policy-Value Network for Image Paragraph Generation. | |
Li et al. | Dataset distillation using parameter pruning | |
CN113254905B (en) | Password dictionary fusion method and system based on probability weight | |
Cheng et al. | Dynamic embedding on textual networks via a gaussian process | |
Wu et al. | Semantic transfer between different tasks in the semantic communication system | |
Fang et al. | Signer-independent sign language recognition based on SOFM/HMM | |
Wang et al. | Spatial-temporal self-attention for asynchronous spiking neural networks | |
Yang et al. | An academic social network friend recommendation algorithm based on decision tree | |
CN110163888A (en) | A kind of novel motion segmentation model quantity detection method | |
Wang et al. | CPR-CLIP: Multimodal Pre-training for Composite Error Recognition in CPR Training | |
CN110909254B (en) | Method and system for predicting question popularity of question-answering community based on deep learning model | |
CN114840873A (en) | Symbolic regression method based on federal genetic programming |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |