CN117216752A - Account password security system based on artificial intelligence - Google Patents
Account password security system based on artificial intelligence Download PDFInfo
- Publication number
- CN117216752A CN117216752A CN202311453819.9A CN202311453819A CN117216752A CN 117216752 A CN117216752 A CN 117216752A CN 202311453819 A CN202311453819 A CN 202311453819A CN 117216752 A CN117216752 A CN 117216752A
- Authority
- CN
- China
- Prior art keywords
- password
- module
- account
- information
- sub
- 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.)
- Pending
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 21
- 238000012549 training Methods 0.000 claims abstract description 62
- 239000002245 particle Substances 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 18
- 238000000034 method Methods 0.000 claims description 16
- 238000003062 neural network model Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000012795 verification Methods 0.000 claims description 11
- 238000012216 screening Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000001816 cooling Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
- Y04S40/20—Information technology specific aspects, e.g. CAD, simulation, modelling, system security
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to the technical field of computers and discloses an account password security system based on artificial intelligence, wherein an information acquisition module is used for acquiring account information to be processed, and the account information comprises a user account and a corresponding account initial password; the security analysis module is used for inputting the account information to be processed into a security analysis model which is obtained through pre-training for analysis, and obtaining a password security analysis result of the account information; the key reconstruction module is used for judging whether the security of the initial password of the account is lower than a preset security threshold value or not based on the password security analysis result, if yes, performing key reconstruction on the initial password of the account to obtain a target password corresponding to the user account; the password encryption module is used for encrypting the target password to obtain encrypted password information, and safely storing the encrypted password information; the invention improves the safety of account information.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an account password security system based on artificial intelligence.
Background
With the rapid development of the internet, various accounts of software applications, forums and the like owned by users are more and more, a plurality of accounts and passwords are required to be managed, a mode strategy for account management is more and more important, a good management mode can improve account security and prevent data leakage, most people like to use birthday passwords at present, the passwords are easy to crack, the security is lower, and therefore, research on an account password security system based on artificial intelligence has important significance for account security.
Disclosure of Invention
The invention aims to solve the problems and designs an account password security system based on artificial intelligence.
The invention provides an account password security system based on artificial intelligence, which comprises an information acquisition module, a security analysis module, a key reconstruction module and a password encryption module, wherein:
the information acquisition module is used for acquiring account information to be processed, wherein the account information comprises a user account and a corresponding account initial password;
the security analysis module is used for inputting the account information to be processed into a security analysis model obtained through pre-training for analysis, so as to obtain a password security analysis result of the account information, wherein the password security analysis result at least comprises five security levels of security, no-alarm, mild alarm, moderate alarm and severe alarm;
the key reconstruction module is used for judging whether the security of the initial password of the account is lower than a preset security threshold value based on the password security analysis result, if yes, performing key reconstruction on the initial password of the account to obtain a target password corresponding to the user account, wherein the security threshold value comprises a security level of light alarm;
the password encryption module is used for encrypting the target password to obtain encrypted password information and safely storing the encrypted password information;
the key reconstruction module comprises a reconstruction request sub-module, a random selection sub-module, a sequence construction sub-module and a password generation sub-module, wherein:
a reconstruction request submodule, configured to obtain a reconstruction request of the account initial password, and prepare a four-particle quantum entanglement state based on the reconstruction request;
the random selecting submodule is used for randomly selecting two particles from the generated four-particle quantum entangled state to form a first quantum sequence, and forming the remaining two four-particle quantum entangled state particles into a second quantum sequence;
the sequence construction submodule is used for randomly inserting the prepared four-particle quantum entanglement state into the first quantum sequence and the second quantum sequence to generate a third quantum sequence, and constructing a bit key sequence based on the third quantum sequence through a quantum channel;
and the password generation sub-module is used for obtaining a target password corresponding to the user account according to the generated two bit keys.
Optionally, in a first implementation manner of the first aspect of the present invention, the security analysis module includes a feature extraction sub-module, a tag matching sub-module, a model training sub-module, a result prediction sub-module, an iteration training sub-module, and a model analysis sub-module, where:
the feature extraction sub-module is used for obtaining an initialization sample, and extracting features of the passwords of the initialization sample to obtain a ciphertext feature set;
the tag matching sub-module is used for matching the ciphertext feature set with the ciphertext tag to obtain a ciphertext feature set containing the tag, and constructing a training set according to the ciphertext feature set containing the tag;
the model training sub-module is used for inputting the training set into a neural network model, acquiring the number of regression trees and a loss function, and training the neural network model to obtain an initial analysis model;
the result prediction sub-module is used for predicting by adopting the initial analysis model, and comparing the obtained prediction result with an original label to obtain the prediction accuracy of the initial analysis model;
the iterative training sub-module is used for modifying the number of regression trees based on the prediction accuracy of the initial analysis model and carrying out iterative training to obtain a safety analysis model with optimal parameters;
and the model analysis sub-module is used for inputting the account information to be processed into the security analysis model for analysis to obtain a password security analysis result of the account information.
Optionally, in a second implementation manner of the first aspect of the present invention, the model training submodule includes a fitting unit, a lifting unit, a joining unit and a traversing unit, where:
the fitting unit is used for randomly sampling the place with the place put back from the training set to obtain a training sample, initializing a prediction result, fitting a regression tree, determining a leaf node area and carrying out fitting residual error;
the lifting unit is used for forming a gradient lifting decision tree model by a plurality of regression trees and taking the gradient lifting decision tree model as a first stage base classifier of the layered model integration framework;
the adding unit is used for adding the prediction result of the first stage base classifier into the training set as a new characteristic to obtain a new training set;
and the traversing unit is used for traversing the new training set to obtain the weight and gradient of the samples in the new training set, updating the regression coefficient, determining the Sigmoid function, outputting the integrated classifier and obtaining the initial analysis model.
Optionally, in a third implementation manner of the first aspect of the present invention, the cipher generating submodule includes a key expansion unit, a random selection unit and a recoding unit, where:
the key expansion unit is used for carrying out key expansion on the bit keys, and each initial key obtains 32 round keys with 32 bits and 96 round keys in total;
the random selection unit is used for randomly selecting 69 use in 96 round keys, randomly selecting 37 of the 69 use round keys to generate 37 corresponding lookup tables, and taking the other 32 use round keys as table selection factors;
and the recoding unit is used for recoding the mapping relation between the plaintext and the ciphertext based on the lookup table and the table selection factor to obtain the target password corresponding to the user account.
Optionally, in a fourth implementation manner of the first aspect of the present invention, the cryptographic module includes an initialization processing sub-module, a character filling sub-module, an encryption processing sub-module, and a tag generating sub-module, where:
the initialization processing sub-module is used for acquiring the target password, initializing the target password, and updating the state of the target password to obtain an initialized state after the initialization processing;
the character filling sub-module is used for acquiring associated data, dividing the associated data into a plurality of blocks containing 32 bytes, filling with 0 characters when the length of the associated data of the last block is smaller than 32 bytes, and updating the initial state;
the encryption processing submodule is used for encrypting the plaintext by using an SM4 encryption algorithm, taking the updated state as a secret key, continuously updating the state by using the ciphertext, and simultaneously carrying out state updating and plaintext encryption;
the tag generation sub-module is used for respectively generating associated data and ciphertext hash values by utilizing a hash function, gradually generating 128-bit states by multiple rounds of transformation, and generating tags by utilizing the states so as to obtain encrypted password information.
Optionally, in a fifth implementation manner of the first aspect of the present invention, the cryptographic module further includes a block screening sub-module, a legal judgment sub-module, a block body replacement sub-module, and a block chain storage sub-module, where:
the block screening sub-module is used for screening out the high-cold blocks in the block chain and broadcasting the block numbers, the storage parts, the storage nodes and the reconstruction information of the high-cold blocks;
the legal judgment sub-module is used for judging the validity of the monitoring node verification information of the high-cold block, and if the information is legal, the monitoring node calculates a random number;
the regional block replacement sub-module is used for updating the random number by a supervision node, the storage node stores regional block information, and after all nodes pass verification, the regional block of the high-temperature cold block is replaced by encrypted password information;
and the blockchain storage sub-module is used for recording the information of the storage process into the blockchain in a transaction information mode.
Optionally, in a sixth implementation manner of the first aspect of the present invention, the operation method of the account password security system based on artificial intelligence includes the following steps:
acquiring account information to be processed, wherein the account information comprises a user account and a corresponding account initial password;
inputting the account information to be processed into a pre-trained security analysis model for analysis to obtain a password security analysis result of the account information;
judging whether the security of the initial password of the account is lower than a preset security threshold value or not based on the password security analysis result, if yes, carrying out key reconstruction on the initial password of the account to obtain a target password corresponding to the user account;
encrypting the target password to obtain encrypted password information, and safely storing the encrypted password information.
Optionally, in a seventh implementation manner of the first aspect of the present invention, inputting the account information to be processed into a security analysis model trained in advance for analysis, to obtain a password security analysis result of the account information, including:
acquiring an initialization sample, and extracting characteristics of a password of the initialization sample to obtain a ciphertext characteristic set;
matching the ciphertext feature set with the ciphertext tag to obtain a ciphertext feature set containing the tag, and constructing a training set according to the ciphertext feature set containing the tag;
inputting the training set into a neural network model, acquiring the number of regression trees and a loss function, and training the neural network model to obtain an initial analysis model;
predicting by adopting the initial analysis model, and comparing the obtained prediction result with an original label to obtain the prediction accuracy of the initial analysis model;
modifying the number of regression trees based on the prediction accuracy of the initial analysis model, and performing iterative training to obtain a safety analysis model with optimal parameters;
inputting the account information to be processed into the security analysis model for analysis to obtain a password security analysis result of the account information.
Optionally, in an eighth implementation manner of the first aspect of the present invention, the securely storing the encrypted password information includes:
screening out a high-cold block in a block chain, and broadcasting the block number, the storage nodes and the reconstruction information of the high-cold block;
judging the validity of the monitoring node verification information of the high-cold block, and if the information is legal, calculating a random number by the monitoring node;
updating the random number by a supervision node, storing the block information by a storage node, and replacing the block of the high-cooling block with encrypted password information after all nodes pass verification;
the information of the stored procedure is recorded in the blockchain in the form of transaction information.
According to the technical scheme provided by the invention, the information acquisition module, the security analysis module, the key reconstruction module and the password encryption module are arranged, and the information acquisition module is used for acquiring account information to be processed, wherein the account information comprises a user account and a corresponding account initial password; the security analysis module is used for inputting the account information to be processed into a security analysis model which is obtained through pre-training for analysis, and obtaining a password security analysis result of the account information; the key reconstruction module is used for judging whether the security of the initial password of the account is lower than a preset security threshold value or not based on the password security analysis result, if yes, performing key reconstruction on the initial password of the account to obtain a target password corresponding to the user account; the password encryption module is used for encrypting the target password to obtain encrypted password information, and safely storing the encrypted password information; according to the invention, the security level analysis is carried out on the current password of the account, and the password reconstruction, encryption and storage processing are carried out according to the security level of the password, so that the security of the account information is improved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention.
FIG. 1 is a schematic diagram of an account password security system based on artificial intelligence according to an embodiment of the present invention;
fig. 2 is a schematic diagram of another structure of an account password security system based on artificial intelligence according to an embodiment of the present invention.
Detailed Description
The terms "first," "second," "third," "fourth" and the like in the description and in the claims and in the above drawings, if any, are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus.
For easy understanding, the following describes a specific flow of an embodiment of the present invention, please refer to fig. 1 for a schematic diagram of an embodiment of an account password security system based on artificial intelligence, which includes an information obtaining module, a security analysis module, a key reconstruction module and a password encryption module, wherein:
the information acquisition module 101 is configured to acquire account information to be processed, where the account information includes a user account and a corresponding account initial password;
the security analysis module 102 is configured to input the account information to be processed into a security analysis model obtained by training in advance for analysis, so as to obtain a password security analysis result of the account information, where the password security analysis result at least includes five security levels of security, no-alert, mild alert, moderate alert and severe alert;
the key reconstruction module 103 is configured to determine, based on a password security analysis result, whether the security of the account initial password is lower than a preset security threshold, and if yes, perform key reconstruction on the account initial password to obtain a target password corresponding to the user account, where the security threshold includes a security level of light alarm;
the password encryption module 104 is configured to encrypt the target password, obtain encrypted password information, and store the encrypted password information securely.
In this embodiment, the operation method of the account password security system based on artificial intelligence includes the following steps: acquiring account information to be processed, wherein the account information comprises a user account and a corresponding account initial password; inputting the account information to be processed into a security analysis model obtained by training in advance for analysis, and obtaining a password security analysis result of the account information; judging whether the security of the account initial password is lower than a preset security threshold value or not based on a password security analysis result, if yes, performing key reconstruction on the account initial password to obtain a target password corresponding to the user account; and encrypting the target password to obtain encrypted password information, and safely storing the encrypted password information.
In the embodiment, an initialization sample is obtained, and the characteristics of the password of the initialization sample are extracted to obtain a ciphertext characteristic set; matching the ciphertext feature set with the ciphertext tag to obtain a ciphertext feature set containing the tag, and constructing a training set according to the ciphertext feature set containing the tag; inputting the training set into a neural network model, acquiring the number of regression trees and a loss function, and training the neural network model to obtain an initial analysis model; predicting by adopting an initial analysis model, and comparing the obtained prediction result with an original label to obtain the prediction accuracy of the initial analysis model; modifying the number of regression trees based on the prediction accuracy of the initial analysis model, and performing iterative training to obtain a safety analysis model with optimal parameters; inputting the account information to be processed into a security analysis model for analysis to obtain a password security analysis result of the account information.
In this embodiment, the high-cold block in the block chain is screened, and the block number, the number of storage, the storage node and the reconstruction information of the high-cold block are broadcasted; judging the validity of the monitoring node verification information of the high-cooling block, and if the information is legal, calculating a random number by the monitoring node; updating the random number by the monitoring node, storing the block information by the storage node, and replacing the block of the high-cooling block with the encrypted password information after all nodes pass verification; the information of the stored procedure is recorded in the blockchain in the form of transaction information.
Referring to fig. 2, a second embodiment of an account password security system based on artificial intelligence according to an embodiment of the present invention is shown, where the system includes an information obtaining module 101, a security analysis module 102, a key reconstruction module 103, and a password encryption module 104;
in this embodiment, the security analysis module 102 includes a feature extraction sub-module, a tag matching sub-module, a model training sub-module, a result prediction sub-module, an iteration training sub-module, and a model analysis sub-module, where:
the feature extraction submodule 1021 is used for obtaining an initialization sample, and extracting features of a password of the initialization sample to obtain a ciphertext feature set;
a tag matching sub-module 1022, configured to match the ciphertext feature set with the ciphertext tag to obtain a ciphertext feature set containing the tag, and construct a training set according to the ciphertext feature set containing the tag;
model training submodule 1023, which is used to input training set into neural network model, and obtain regression tree number and loss function, train neural network model, and obtain initial analysis model;
the result prediction submodule 1024 is configured to perform prediction by using an initial analysis model, and compare the obtained prediction result with the original label to obtain a prediction accuracy of the initial analysis model;
the iterative training submodule 1025 is used for modifying the number of regression trees based on the prediction accuracy of the initial analysis model and carrying out iterative training to obtain a safety analysis model with optimal parameters;
the model analysis submodule 1026 is configured to input the account information to be processed into the security analysis model for analysis, so as to obtain a password security analysis result of the account information.
In this embodiment, the model training submodule includes a fitting unit, a lifting unit, a joining unit and a traversing unit, where:
the fitting unit is used for randomly sampling the ground with the return from the training set to obtain a training sample, initializing a prediction result, fitting a regression tree, determining a leaf node area and carrying out fitting residual error;
the lifting unit is used for forming a gradient lifting decision tree model by a plurality of regression trees and taking the gradient lifting decision tree model as a first stage base classifier of the layered model integration framework;
the adding unit is used for adding the prediction result of the first stage base classifier as a new feature into the training set to obtain a new training set;
the traversal unit is used for traversing the new training set to obtain the weight and gradient of the sample in the new training set, updating the regression coefficient, determining the Sigmoid function, outputting the integrated classifier and obtaining the initial analysis model.
In this embodiment, the key reconstruction module 103 includes a reconstruction request sub-module, a random selection sub-module, a sequence construction sub-module, and a password generation sub-module, where:
a reconstruction request submodule 1031, configured to obtain a reconstruction request of an account initial password, and prepare a four-particle quantum entanglement state based on the reconstruction request;
a random selecting sub-module 1032, configured to randomly select two particles from the generated four-particle quantum entangled state to form a first quantum sequence, and form the remaining two four-particle quantum entangled state particles to form a second quantum sequence;
a sequence construction submodule 1033, configured to randomly insert the prepared four-particle quantum entangled state into the first quantum sequence and the second quantum sequence to generate a third quantum sequence, and construct a bit key sequence based on the third quantum sequence by using the generated new quantum sequence through a quantum channel;
and the password generating submodule 1034 is used for obtaining a target password corresponding to the user account according to the generated two bit keys.
In this embodiment, the password generating submodule includes a key expansion unit, a random selection unit and a recoding unit, where:
the key expansion unit is used for carrying out key expansion on the bit keys, and each initial key obtains 32 round keys with 32 bits and 96 round keys in total;
the random selection unit is used for randomly selecting 69 use in 96 round keys, randomly selecting 37 of the 69 use round keys to generate 37 corresponding lookup tables, and taking the other 32 use round keys as table selection factors;
and the recoding unit is used for recoding the mapping relation between the plaintext and the ciphertext based on the lookup table and the table selection factor to obtain a target password corresponding to the user account.
In this embodiment, the cryptographic module 104 includes an initialization processing sub-module, a character filling sub-module, an encryption processing sub-module, and a tag generation sub-module, where:
the initialization processing sub-module 1041 is configured to obtain a target password, perform initialization processing on the target password, and update a state of the target password to obtain an initial state after the initialization processing;
the character filling submodule 1042 is used for acquiring the associated data, dividing the associated data into a plurality of blocks containing 32 bytes, filling with 0 characters when the length of the associated data of the last block is smaller than 32 bytes, and updating the initial state;
an encryption processing submodule 1043, configured to encrypt the plaintext using the SM4 encryption algorithm, use the updated state as a key, and continuously update the state using the ciphertext, where the state update is performed simultaneously with the plaintext encryption;
the tag generation sub-module 1044 is configured to generate the associated data and the ciphertext hash value by using the hash function, gradually generate a 128-bit state by multiple rounds of transformation, and generate a tag by using the state, so as to obtain encrypted password information.
In this embodiment, the cryptographic module further includes a block screening submodule, a legal judgment submodule, a block body replacement submodule, and a block chain storage submodule, where:
the block screening submodule 1045 is configured to screen out a high-cold block in the blockchain, and broadcast the block number, the number of stored copies, the storage node and the reconstruction information of the high-cold block;
a legal judgment submodule 1046, configured to judge validity of the information verified by the supervisory node of the high-cold block, and if the information verified by the supervisory node is legal, calculate a random number;
the block replacement sub-module 1047 is configured to update the random number by the supervisory node, store the block information by the storage node, and replace the block of the high-cooling block with the encrypted password information after all nodes pass the verification;
the blockchain storage submodule 1048 is configured to record information of the stored procedure into the blockchain in a manner of transaction information.
In this embodiment, the SM4 algorithm is a Feistel structure-based selective block encryption algorithm, and is composed of an encryption and decryption algorithm and a key expansion algorithm, where the encryption and decryption algorithm and the key expansion algorithm both adopt a 32-round nonlinear iterative structure, the plaintext block length and the cipher length of the SM4 algorithm are both 128 bits, and the SM4 block algorithm is used to block the plaintext according to the length of 128 bits, and then encrypt each block data by using the same key, so as to convert each block data into a block cipher with the same length. The specific algorithm process comprises the following steps: and (4) generating a key, selecting an initial key, and calling a key expansion algorithm to obtain 32 round keys. The encryption is carried out by using 32 round keys to carry out 32 rounds of iteration on plaintext, the data after iteration is subjected to one-time reverse order transformation to obtain ciphertext, the encryption is completed, and because the Feistel structure is a symmetrical encryption and decryption structure, the decryption algorithm uses the round function structure and the initial key which are the same as the encryption algorithm, and also comprises 32 rounds of iteration and one-time reverse order transformation, but in the process of round iteration, the use sequence of the round keys is opposite, namely the round keys of the decryption algorithm are the reverse sequence of the round keys of the encryption algorithm, and the decryption is the reverse process of encryption.
Through implementation of the scheme, the system comprises an information acquisition module, a security analysis module, a key reconstruction module and a password encryption module, the security level analysis is carried out on the current password of the account, the password reconstruction, encryption and storage processing are carried out according to the security level of the password, and the security of the account information is improved.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the above-described embodiments, and that the above-described embodiments and descriptions are only preferred embodiments of the present invention, and are not intended to limit the invention, and that various changes and modifications may be made therein without departing from the spirit and scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (9)
1. The account password security system based on the artificial intelligence is characterized by comprising an information acquisition module, a security analysis module, a key reconstruction module and a password encryption module, wherein:
the information acquisition module is used for acquiring account information to be processed, wherein the account information comprises a user account and a corresponding account initial password;
the security analysis module is used for inputting the account information to be processed into a security analysis model obtained through pre-training for analysis, so as to obtain a password security analysis result of the account information, wherein the password security analysis result at least comprises five security levels of security, no-alarm, mild alarm, moderate alarm and severe alarm;
the key reconstruction module is used for judging whether the security of the initial password of the account is lower than a preset security threshold value based on the password security analysis result, if yes, performing key reconstruction on the initial password of the account to obtain a target password corresponding to the user account, wherein the security threshold value comprises a security level of light alarm;
the password encryption module is used for encrypting the target password to obtain encrypted password information and safely storing the encrypted password information;
the key reconstruction module comprises a reconstruction request sub-module, a random selection sub-module, a sequence construction sub-module and a password generation sub-module, wherein:
a reconstruction request submodule, configured to obtain a reconstruction request of the account initial password, and prepare a four-particle quantum entanglement state based on the reconstruction request;
the random selecting submodule is used for randomly selecting two particles from the generated four-particle quantum entangled state to form a first quantum sequence, and forming the remaining two four-particle quantum entangled state particles into a second quantum sequence;
the sequence construction submodule is used for randomly inserting the prepared four-particle quantum entanglement state into the first quantum sequence and the second quantum sequence to generate a third quantum sequence, and constructing a bit key sequence based on the third quantum sequence through a quantum channel;
and the password generation sub-module is used for obtaining a target password corresponding to the user account according to the generated two bit keys.
2. The account password security system based on artificial intelligence of claim 1, wherein the security analysis module comprises a feature extraction sub-module, a tag matching sub-module, a model training sub-module, a result prediction sub-module, an iterative training sub-module, and a model analysis sub-module, wherein:
the feature extraction sub-module is used for obtaining an initialization sample, and extracting features of the passwords of the initialization sample to obtain a ciphertext feature set;
the tag matching sub-module is used for matching the ciphertext feature set with the ciphertext tag to obtain a ciphertext feature set containing the tag, and constructing a training set according to the ciphertext feature set containing the tag;
the model training sub-module is used for inputting the training set into a neural network model, acquiring the number of regression trees and a loss function, and training the neural network model to obtain an initial analysis model;
the result prediction sub-module is used for predicting by adopting the initial analysis model, and comparing the obtained prediction result with an original label to obtain the prediction accuracy of the initial analysis model;
the iterative training sub-module is used for modifying the number of regression trees based on the prediction accuracy of the initial analysis model and carrying out iterative training to obtain a safety analysis model with optimal parameters;
and the model analysis sub-module is used for inputting the account information to be processed into the security analysis model for analysis to obtain a password security analysis result of the account information.
3. The account password security system based on artificial intelligence of claim 2, wherein the model training submodule comprises a fitting unit, a lifting unit, a joining unit and a traversing unit, wherein:
the fitting unit is used for randomly sampling the place with the place put back from the training set to obtain a training sample, initializing a prediction result, fitting a regression tree, determining a leaf node area and carrying out fitting residual error;
the lifting unit is used for forming a gradient lifting decision tree model by a plurality of regression trees and taking the gradient lifting decision tree model as a first stage base classifier of the layered model integration framework;
the adding unit is used for adding the prediction result of the first stage base classifier into the training set as a new characteristic to obtain a new training set;
and the traversing unit is used for traversing the new training set to obtain the weight and gradient of the samples in the new training set, updating the regression coefficient, determining the Sigmoid function, outputting the integrated classifier and obtaining the initial analysis model.
4. The account password security system based on artificial intelligence of claim 1, wherein the password generation submodule comprises a key expansion unit, a random selection unit and a recoding unit, wherein:
the key expansion unit is used for carrying out key expansion on the bit keys, and each initial key obtains 32 round keys with 32 bits and 96 round keys in total;
the random selection unit is used for randomly selecting 69 use in 96 round keys, randomly selecting 37 of the 69 use round keys to generate 37 corresponding lookup tables, and taking the other 32 use round keys as table selection factors;
and the recoding unit is used for recoding the mapping relation between the plaintext and the ciphertext based on the lookup table and the table selection factor to obtain the target password corresponding to the user account.
5. The artificial intelligence based account password security system of claim 1, wherein the password encryption module comprises an initialization processing sub-module, a character population sub-module, an encryption processing sub-module, and a tag generation sub-module, wherein:
the initialization processing sub-module is used for acquiring the target password, initializing the target password, and updating the state of the target password to obtain an initialized state after the initialization processing;
the character filling sub-module is used for acquiring associated data, dividing the associated data into a plurality of blocks containing 32 bytes, filling with 0 characters when the length of the associated data of the last block is smaller than 32 bytes, and updating the initial state;
the encryption processing submodule is used for encrypting the plaintext by using an SM4 encryption algorithm, taking the updated state as a secret key, continuously updating the state by using the ciphertext, and simultaneously carrying out state updating and plaintext encryption;
the tag generation sub-module is used for respectively generating associated data and ciphertext hash values by utilizing a hash function, gradually generating 128-bit states by multiple rounds of transformation, and generating tags by utilizing the states so as to obtain encrypted password information.
6. The account password security system of claim 1, wherein the password encryption module further comprises a block screening sub-module, a legal judgment sub-module, a block body replacement sub-module, and a blockchain storage sub-module, wherein:
the block screening sub-module is used for screening out the high-cold blocks in the block chain and broadcasting the block numbers, the storage parts, the storage nodes and the reconstruction information of the high-cold blocks;
the legal judgment sub-module is used for judging the validity of the monitoring node verification information of the high-cold block, and if the information is legal, the monitoring node calculates a random number;
the regional block replacement sub-module is used for updating the random number by a supervision node, the storage node stores regional block information, and after all nodes pass verification, the regional block of the high-temperature cold block is replaced by encrypted password information;
and the blockchain storage sub-module is used for recording the information of the storage process into the blockchain in a transaction information mode.
7. An artificial intelligence based account password security system as recited in claim 1, wherein the method of operating the artificial intelligence based account password security system comprises the steps of:
acquiring account information to be processed, wherein the account information comprises a user account and a corresponding account initial password;
inputting the account information to be processed into a pre-trained security analysis model for analysis to obtain a password security analysis result of the account information;
judging whether the security of the initial password of the account is lower than a preset security threshold value or not based on the password security analysis result, if yes, carrying out key reconstruction on the initial password of the account to obtain a target password corresponding to the user account;
encrypting the target password to obtain encrypted password information, and safely storing the encrypted password information.
8. The account password security system of claim 7, wherein inputting the account information to be processed into a pre-trained security analysis model for analysis to obtain a password security analysis result of the account information comprises:
acquiring an initialization sample, and extracting characteristics of a password of the initialization sample to obtain a ciphertext characteristic set;
matching the ciphertext feature set with the ciphertext tag to obtain a ciphertext feature set containing the tag, and constructing a training set according to the ciphertext feature set containing the tag;
inputting the training set into a neural network model, acquiring the number of regression trees and a loss function, and training the neural network model to obtain an initial analysis model;
predicting by adopting the initial analysis model, and comparing the obtained prediction result with an original label to obtain the prediction accuracy of the initial analysis model;
modifying the number of regression trees based on the prediction accuracy of the initial analysis model, and performing iterative training to obtain a safety analysis model with optimal parameters;
inputting the account information to be processed into the security analysis model for analysis to obtain a password security analysis result of the account information.
9. An artificial intelligence based account password security system as claimed in claim 7, wherein said securely storing said encrypted password information comprises:
screening out a high-cold block in a block chain, and broadcasting the block number, the storage nodes and the reconstruction information of the high-cold block;
judging the validity of the monitoring node verification information of the high-cold block, and if the information is legal, calculating a random number by the monitoring node;
updating the random number by a supervision node, storing the block information by a storage node, and replacing the block of the high-cooling block with encrypted password information after all nodes pass verification;
the information of the stored procedure is recorded in the blockchain in the form of transaction information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311453819.9A CN117216752A (en) | 2023-11-03 | 2023-11-03 | Account password security system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311453819.9A CN117216752A (en) | 2023-11-03 | 2023-11-03 | Account password security system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117216752A true CN117216752A (en) | 2023-12-12 |
Family
ID=89042808
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311453819.9A Pending CN117216752A (en) | 2023-11-03 | 2023-11-03 | Account password security system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117216752A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2382503C1 (en) * | 2008-09-05 | 2010-02-20 | Федеральное Государственное Унитарное Предприятие "Концерн "Системпром" | Method of transmitting private key in quantum cryptographic systems |
| CN108540426A (en) * | 2017-03-02 | 2018-09-14 | 珠海金山办公软件有限公司 | A kind of method, apparatus and server for realizing data processing |
| US20200028673A1 (en) * | 2014-07-28 | 2020-01-23 | The Boeing Company | Content Encryption and Decryption Using a Custom Key |
| CN110807476A (en) * | 2019-10-17 | 2020-02-18 | 新华三信息安全技术有限公司 | Password security level classification method and device and electronic equipment |
| CN114499862A (en) * | 2022-04-06 | 2022-05-13 | 北京微芯感知科技有限公司 | Symmetric key pool encryption and transmission method based on quantum key distribution |
| CN116170137A (en) * | 2023-02-14 | 2023-05-26 | 深圳市真数智能科技有限公司 | Data security privacy protection and system method based on quantum cryptography |
| US20230188222A1 (en) * | 2021-12-02 | 2023-06-15 | Qulabz Inc. | Measurement device independent quantum secure direct communication with user authentication |
| CN116668010A (en) * | 2023-04-25 | 2023-08-29 | 五邑大学 | Password generation method, system, device and storage medium thereof |
-
2023
- 2023-11-03 CN CN202311453819.9A patent/CN117216752A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU2382503C1 (en) * | 2008-09-05 | 2010-02-20 | Федеральное Государственное Унитарное Предприятие "Концерн "Системпром" | Method of transmitting private key in quantum cryptographic systems |
| US20200028673A1 (en) * | 2014-07-28 | 2020-01-23 | The Boeing Company | Content Encryption and Decryption Using a Custom Key |
| CN108540426A (en) * | 2017-03-02 | 2018-09-14 | 珠海金山办公软件有限公司 | A kind of method, apparatus and server for realizing data processing |
| CN110807476A (en) * | 2019-10-17 | 2020-02-18 | 新华三信息安全技术有限公司 | Password security level classification method and device and electronic equipment |
| US20230188222A1 (en) * | 2021-12-02 | 2023-06-15 | Qulabz Inc. | Measurement device independent quantum secure direct communication with user authentication |
| CN114499862A (en) * | 2022-04-06 | 2022-05-13 | 北京微芯感知科技有限公司 | Symmetric key pool encryption and transmission method based on quantum key distribution |
| CN116170137A (en) * | 2023-02-14 | 2023-05-26 | 深圳市真数智能科技有限公司 | Data security privacy protection and system method based on quantum cryptography |
| CN116668010A (en) * | 2023-04-25 | 2023-08-29 | 五邑大学 | Password generation method, system, device and storage medium thereof |
Non-Patent Citations (6)
| Title |
|---|
| 李新刚;贾振红;: "带身份认证的四量子纠缠量子密钥分发协议", 光电子.激光, no. 09 * |
| 李胡 等: "流密码框架下的SM4专用认证加密算法", 《计算机工程与应用》, pages 1 - 8 * |
| 杨亚涛 等: "WBDL：改进的SM4动态白盒密码算法", 《密码学报》, pages 797 - 812 * |
| 王爱兵: "基于量子密码的网络信息安全动态防护方法", 《信息与电脑(理论版)》, pages 212 - 214 * |
| 胡宁玉 等: "基于变色龙hash的区块链可扩展存储方案", 《计算机应用研究》, pages 3539 - 3550 * |
| 袁科 等: "基于混合梯度提升决策树和逻辑回归模型的分组密码算法识别方法", 《工程科学与技术》, pages 218 - 227 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| So | Deep learning‐based cryptanalysis of lightweight block ciphers | |
| CN106776904B (en) | The fuzzy query encryption method of dynamic authentication is supported in a kind of insincere cloud computing environment | |
| CN100536393C (en) | Secret shared key mechanism based user management method | |
| US8429720B2 (en) | Method and apparatus for camouflaging of data, information and functional transformations | |
| JPWO2005031579A1 (en) | Tag privacy protection method, tag device, back-end device, update device, update request device, program thereof, and recording medium storing these programs | |
| Bringer et al. | Identification with encrypted biometric data | |
| US7454782B2 (en) | Method and system for camouflaging access-controlled data | |
| CN108833361B (en) | Identity authentication method and device based on virtual account | |
| CN106612320A (en) | Encrypted data dereplication method for cloud storage | |
| KR101398216B1 (en) | Method for searchable encryption and method for searching of encrypted data | |
| CN110771190A (en) | Controlling access to data | |
| CN108197496A (en) | Data safety Enhancement Method under cloud computing environment | |
| CN107294701B (en) | Multidimensional ciphertext interval query device and method with efficient key management | |
| CN110222520B (en) | Keyword query method for supporting graph encrypted data in cloud environment | |
| CN107908779A (en) | The searching method of dynamic multi-attribute connection keyword based on MAT trees under cloud environment | |
| CN110188545B (en) | Data encryption method and device based on chained database | |
| CN111091381A (en) | Hardware wallet and management method thereof | |
| Iftikhar et al. | A survey on reversible watermarking techniques for relational databases | |
| CN116861460A (en) | Customer data encryption method based on E-commerce marketing | |
| CN111711521B (en) | Block chain account private key resetting method and system | |
| CN108259606A (en) | Cloud computing public cloud file stores and search method | |
| CN112951433A (en) | Mental health assessment method based on privacy calculation | |
| CN108269610A (en) | Data reliability verifying method based on cloud computing | |
| KR101232385B1 (en) | Searchable Symmetric Encryption Method and System | |
| CN117216752A (en) | Account password security system based on artificial intelligence |
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 |