Data encryption model modeling, method of use, and related devices

Abstract

The embodiment of the present disclosure provides a data encryption model modeling method, a use method and device, a computer readable storage medium and an electronic device, and belongs to the technical field of computer and communication. The modeling method comprises the following steps: obtaining a training data set of encrypted data; extracting optimal classification features and optimal split points of the training data set; constructing a decision tree according to the optimal classification features and the optimal split points; and training the decision tree by using the training data set through a random forest algorithm to complete the modeling of the data encryption model. The modeling method of the present disclosure can realize the modeling of the data encryption model.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of computer and communication technology, and in particular, to a data encryption model modeling method and device, a computer readable storage medium and an electronic device. BACKGROUND

[0002] In the process of information transmission, four threats of interception, interruption, tampering and forgery may occur, which seriously reduces the integrity, availability and confidentiality of information, and affects information security. Encryption technology is a powerful weapon against these four security threats. Good encryption technology can hide its identity so that it cannot be interrupted and intercepted. If necessary, verification information can be added to check whether it has been tampered with and forged. Therefore, under the background of the Internet, the demand for encryption technology is more urgent, the requirements are higher, and its role is becoming more and more important.

[0003] It should be noted that the information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0004] The embodiments of the present disclosure provide a data encryption model modeling method and device, a computer readable storage medium and an electronic device, which can realize the modeling of the data encryption model.

[0005] Other characteristics and advantages of the present disclosure will become apparent from the following detailed description, or will be learned by practice of the present disclosure.

[0006] According to one aspect of the present disclosure, a data encryption model modeling method is provided, comprising:

[0007] obtaining a training data set of encrypted data;

[0008] extracting optimal classification features and optimal split points of the training data set;

[0009] constructing a decision tree according to the optimal classification features and the optimal split points;

[0010] training the decision tree using the training data set by a random forest algorithm to complete the modeling of the data encryption model.

[0011] In one embodiment, constructing a decision tree according to the optimal classification features and the optimal split points comprises:

[0012] constructing the decision tree using a classification and regression tree according to the optimal classification features and the optimal split points.

[0013] According to one aspect of the present disclosure, a data encryption model using method is provided, comprising:

[0014] obtaining user input data;

[0015] extracting features of the user input data;

[0016] traversing a decision tree according to the features of the user input data to select an encryption classification path;

[0017] obtaining encrypted data of the user input data through the encryption classification path.

[0018] In one embodiment, the method further comprises:

[0019] performing random perturbation encryption on the encrypted data after sorting the encrypted data according to size.

[0020] In one embodiment, the method further comprises:

[0021] when the user input data is input for the first time, saving the encrypted data.

[0022] In one embodiment, the method further comprises:

[0023] when the user input data is not input for the first time, matching the encrypted data with historically stored encrypted data.

[0024] In one embodiment, the method further comprises:

[0025] using a Boolean variable polynomial to represent an output result of the decision tree.

[0026] According to one aspect of the present disclosure, there is provided a modeling device of a data encryption model, comprising:

[0027] an obtaining module configured to obtain a training data set of encrypted data;

[0028] an extracting module configured to extract optimal classification features and optimal split points of the training data set;

[0029] a constructing module configured to construct a decision tree according to the optimal classification features and the optimal split points;

[0030] a training module configured to train the decision tree using the training data set through a random forest algorithm to complete modeling of the data encryption model.

[0031] According to one aspect of the present disclosure, there is provided an electronic device, comprising:

[0032] one or more processors;

[0033] a memory device configured to store one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method according to any one of the above embodiments.

[0034] According to an aspect of the present disclosure, there is provided a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the method according to any one of the above embodiments.

[0035] In the technical solutions provided by some embodiments of the present disclosure, modeling of a data encryption model can be achieved.

[0036] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0037] The following drawings describe certain illustrative embodiments of the present disclosure, in which the same reference signs represent the same elements. These described embodiments will be exemplary embodiments of the present disclosure, but are not limited in any way.

[0038] Figure 1 A schematic diagram of an exemplary system architecture to which the data encryption model modeling method according to embodiments of the present disclosure can be applied is shown;

[0039] Figure 2 A structural schematic diagram of a computer system of an electronic device suitable for implementing embodiments of the present disclosure is shown;

[0040] Figure 3 A flowchart of the data encryption model modeling method according to an embodiment of the present disclosure is shown schematically;

[0041] Figure 4 is a flowchart of an embodiment of the present disclosure;

[0042] Figure 5 is a schematic diagram of the principle of a random forest algorithm according to an embodiment of the present disclosure;

[0043] Figure 6 A schematic diagram of a modeling device of a data encryption model according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0044] Example embodiments now will be described more fully hereinafter with reference to the accompanying drawings. Example embodiments, may, however, be implemented in many different forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the example embodiments to those skilled in the art.

[0045] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the

[0046] The block diagrams in the drawings show only the functional entities and not necessarily the physical separation of the functional entities. That is, the functional entities can be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0047] The flow diagrams shown in the drawings are merely examples and not necessarily to be construed as having all content and operations / steps, nor necessarily to be executed in the order described. For example, some operations / steps can be further divided, and some operations / steps can be combined or partially combined, so that the actual execution order can be changed according to actual conditions.

[0048] Figure 1 A schematic diagram of an exemplary system architecture 100 is shown, to which the data encryption model modeling method according to embodiments of the disclosure can be applied.

[0049] As shown in Figure 1 The system architecture 100 can include one or more of terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is a medium to provide a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0050] It should be understood that Figure 1 The number of terminal devices, networks, and servers in

[0051] The staff can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. The terminal devices 101, 102, 103 can be various electronic devices with display screens, including but not limited to smartphones, tablet computers, portable computers and desktop computers, digital movie projectors, etc.

[0052] Server 105 can be a server providing various services. For example, a staff member can send a data encryption model modeling request to server 105 using terminal device 103 (or terminal device 101 or 102). Server 105 can obtain the training dataset of the encrypted data; extract the optimal classification features and optimal split points from the training dataset; construct a decision tree based on the optimal classification features and optimal split points; and train the decision tree using the training dataset through a random forest algorithm to complete the data encryption model modeling. Server 105 can display the trained data encryption model on terminal device 103, allowing staff members to view the data encryption model based on the content displayed on terminal device 103.

[0053] For example, terminal device 103 (which could also be terminal device 101 or 102) could be a smart TV, a VR (Virtual Reality) / AR (Augmented Reality) headset, or a mobile terminal such as a smartphone or tablet with navigation, ride-hailing, instant messaging, or video applications (APPs) installed on it. Staff can send a data encryption modeling request to server 105 through the smart TV, VR / AR headset, or the navigation, ride-hailing, instant messaging, or video APP. Server 105 can obtain the data encryption model based on the data encryption modeling request and return the data encryption model to the smart TV, VR / AR headset, or the navigation, ride-hailing, instant messaging, or video APP, and then display the data encryption model through the smart TV, VR / AR headset, or the navigation, ride-hailing, instant messaging, or video APP.

[0054] Figure 2 A schematic diagram of the structure of a computer system suitable for implementing the embodiments of the present disclosure is shown.

[0055] It should be noted that, Figure 2 The computer system 200 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0056] like Figure 2As shown, the computer system 200 includes a central processing unit (CPU) 201, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 202 or programs loaded from storage section 208 into random access memory (RAM) 203. The RAM 203 also stores various programs and data required for system operation. The CPU 201, ROM 202, and RAM 203 are interconnected via a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0057] The following components are connected to I / O interface 205: an input section 206 including a keyboard, mouse, etc.; an output section 207 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 208 including a hard disk, etc.; and a communication section 209 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 209 performs communication processing via a network such as the Internet. A drive 210 is also connected to I / O interface 205 as needed. Removable media 211, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 210 as needed so that computer programs read from them can be installed into storage section 208 as needed.

[0058] In particular, according to embodiments of this disclosure, the processes described below with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 209, and / or installed from removable medium 211. When the computer program is executed by central processing unit (CPU) 201, it performs various functions defined in the methods and / or apparatus of this application.

[0059] It should be noted that the computer-readable storage medium disclosed herein may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. The transmitted data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF (Radio Frequency), etc., or any suitable combination thereof.

[0060] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of methods, apparatus, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions selected in the blocks may occur in a different order than those shown in the drawings. For example, two consecutively represented blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0061] The modules and / or units and / or sub-units described in the embodiments of this disclosure can be implemented in software or hardware, and the described modules and / or units and / or sub-units can also be located in a processor. The names of these modules and / or units and / or sub-units do not, in some cases, constitute a limitation on the module and / or unit and / or sub-unit itself.

[0062] On the other hand, this application also provides a computer-readable storage medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable storage medium carries one or more programs that, when executed by the electronic device, cause the electronic device to perform the methods described in the following embodiments. For example, the electronic device may perform... Figure 3 Each step.

[0063] In related technologies, for example, machine learning methods and deep learning methods can be used to model data encryption, and different methods have different applicable scopes.

[0064] Figure 3 A flowchart illustrating a data encryption modeling method according to an embodiment of the present disclosure is shown schematically. The method steps of this embodiment can be executed by a terminal device, by a server, or by interaction between the terminal device and the server. For example, they can be executed by the methods described above. Figure 1 The server 105 in the middle executes, but this disclosure is not limited thereto.

[0065] In step S310, the training dataset of encrypted data is obtained.

[0066] In this step, the terminal device or server obtains the training dataset of encrypted data.

[0067] In this disclosure, the terminal device can be implemented in various forms. For example, the terminal described in this disclosure may include mobile terminals such as mobile phones, tablets, laptops, handheld computers, personal digital assistants (PDAs), portable media players (PMPs), data encryption modeling devices, wearable devices, smart bracelets, pedometers, robots, and self-driving cars, as well as fixed terminals such as digital TVs and desktop computers.

[0068] In step S320, the optimal classification features and optimal split points of the training dataset are extracted.

[0069] In this step, the terminal device or server extracts the optimal classification features and optimal split points from the training dataset.

[0070] In step S330, a decision tree is constructed based on the optimal classification features and the optimal split point.

[0071] In this step, the terminal device or server constructs a decision tree based on the optimal classification features and the optimal split point.

[0072] In one embodiment, constructing a decision tree based on the optimal classification feature and the optimal split point includes:

[0073] The decision tree is constructed using classification and regression trees based on the optimal classification features and the optimal split point.

[0074] In step S340, the decision tree is trained using the training dataset through the random forest algorithm to complete the modeling of the data encryption model.

[0075] In this step, the terminal device or server trains the decision tree using the training dataset through the random forest algorithm to complete the modeling of the data encryption model.

[0076] Random forest is a supervised learning algorithm in machine learning. It uses the bootstrap resampling technique to randomly draw n samples with replacement from the training sample set to generate a new training sample set to train decision trees. Then, it generates m decision trees to form a random forest. The algorithm usually chosen is the classification and regression tree (CART) decision tree.

[0077] In this disclosure, the server can only access the encrypted data and cannot access the original data. It is secure during the use of FHE (Fully Homomorphic Encryption).

[0078] In this disclosure, the client cannot know the model on the server side because the server side performs a multinomial P-based evaluation, and due to the characteristics of the comparison protocol, the client cannot obtain the parameters of the model learned at the nodes inside the tree.

[0079] This application includes a method for using a data encryption model, comprising:

[0080] Get user input data;

[0081] Extract features from the user input data;

[0082] The encrypted classification path is selected by traversing the decision tree based on the features of the user input data.

[0083] The encrypted data of the user input data is obtained through the encrypted classification path.

[0084] In one embodiment, the method includes:

[0085] The encrypted data is sorted by size and then encrypted using random perturbation.

[0086] In one embodiment, the method includes:

[0087] When the user inputs data for the first time, the encrypted data is saved.

[0088] In one embodiment, the method includes:

[0089] When the data input by the user is not the first time, the encrypted data is matched with the encrypted data stored in history.

[0090] In one embodiment, the method includes:

[0091] The output of the decision tree is represented using a Boolean variable polynomial.

[0092] In one embodiment of this disclosure, the following steps are included:

[0093] 1. Generate optimal classification features and optimal split points.

[0094] a. Determine the number of features in each sample;

[0095] b. Set the optimal split point;

[0096] c. Iterate through all features and extract the possible values ​​contained in the [i]th feature, remove duplicate features, and find the Gini index for each feature;

[0097] d. Select the set split point values, and choose the largest feature as the split point to divide the dataset into subsets and calculate the Gini index;

[0098] e. Select the optimal classification features and the optimal splitting points;

[0099] 2. Decision Tree Construction

[0100] a. Select the CART decision tree generation algorithm;

[0101] b. A recursive function is used to generate each subtree and construct a decision tree based on the optimal classification feature and the optimal split point;

[0102] 3. Comparison Protocol

[0103] Assume there is a computational method A. If A has k values ​​a1 and ak, A first sorts and encrypts the sequence according to its size, and then sends the encrypted results to B in pairs. B determines the larger value of each pair by comparison, and finally obtains the index m corresponding to the maximum value.

[0104] 4. Multinomial Decision Tree

[0105] Encrypted decision trees require the client's input x to traverse the server-side decision tree model, but the traversal path remains unknown, as the path's position and length within the tree could leak information about the server model. This scheme uses polynomials based on Boolean variables to represent the decision tree's output. Each node corresponds to a Boolean variable, the value of which determines whether the left or right branch is visited next.

[0106] Figure 4 This is a flowchart illustrating an embodiment of the present disclosure.

[0107] Figure 5 This is a schematic diagram illustrating the principle of a random forest algorithm according to an embodiment of this disclosure.

[0108] This disclosure uses encrypted decision trees and encrypted random forest algorithms to construct decision trees using a multi-party computation scheme. This disclosure implements random permutations and random perturbations of the computation parties, and then sends the encrypted results in pairs. It also determines the larger value of each pair by comparison, and finally obtains the index m corresponding to the maximum value. The encrypted decision tree of this disclosure requires that the client's input x can traverse the decision tree model on the server side. The scheme uses a polynomial based on Boolean variables to represent the output results of the decision tree.

[0109] Figure 6 A schematic diagram of a modeling apparatus for a data encryption model according to an embodiment of the present disclosure is shown.

[0110] The modeling apparatus 600 for the data encryption model provided in this embodiment may include an acquisition module 610, an extraction module 620, a construction module 630, and a training module 640.

[0111] The acquisition module is configured to acquire the training dataset containing encrypted data.

[0112] The extraction module is configured to extract the optimal classification features and optimal split points from the training dataset;

[0113] The construction module is configured to construct a decision tree based on the optimal classification features and the optimal split point;

[0114] The training module is configured to train the decision tree using the training dataset through the random forest algorithm to complete the modeling of the data encryption model.

[0115] According to embodiments of this disclosure, the modeling apparatus 600 for the data encryption model described above can be used in the data encryption model usage method described in this disclosure.

[0116] It is understood that the acquisition module 610, extraction module 620, construction module 630, and training module 640 can be implemented in a single module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functionality of one or more of these modules can be combined with at least some of the functionality of other modules and implemented in a single module. According to embodiments of the present invention, at least one of the acquisition module 610, extraction module 620, construction module 630, and training module 640 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or can be implemented in hardware or firmware in any other reasonable manner of integrating or packaging circuitry, or in a suitable combination of software, hardware, and firmware implementations. Alternatively, at least one of the acquisition module 610, extraction module 620, construction module 630, and training module 640 can be at least partially implemented as a computer program module, which, when run by a computer, can execute the functions of the corresponding module.

[0117] It should be noted that although several modules, units, and sub-units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules, units, and sub-units described above can be embodied in a single module, unit, or sub-unit. Conversely, the features and functions of a single module, unit, and sub-unit described above can be further divided into multiple modules, units, and sub-units.

[0118] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this disclosure.

[0119] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0120] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A modeling method for a data encryption model, characterized in that, include: Obtain the training dataset containing encrypted data; Extract the optimal classification features and optimal split points from the training dataset; Construct a decision tree based on the optimal classification features and the optimal splitting points; The decision tree is trained using the training dataset through the random forest algorithm to complete the modeling of the data encryption model; The output of the decision tree is represented using a Boolean variable polynomial, and each node in the decision tree corresponds to a Boolean variable. The process of extracting the optimal classification feature and the optimal split point from the training dataset includes: determining the number of features for each sample in the training dataset, traversing all features and extracting the possible values ​​of each feature, calculating the Gini index of each feature after deduplication, dividing the dataset into sub-datasets with the largest feature as the split point and calculating the Gini index of the sub-datasets, extracting the optimal classification feature based on the Gini index of each feature, and extracting the optimal split point based on the Gini index of the sub-datasets.

2. The method according to claim 1, characterized in that, Constructing a decision tree based on the optimal classification feature and the optimal split point includes: The decision tree is constructed using classification and regression trees based on the optimal classification features and the optimal split point.

3. A method for using a data encryption model, characterized in that, include: Get user input data; Extract features from the user input data; The encrypted classification path is selected by traversing the decision tree based on the features of the user input data. The encrypted data of the user input data is obtained through the encrypted classification path; The output of the decision tree is represented using a Boolean variable polynomial, and each node in the decision tree corresponds to a Boolean variable. The decision tree is constructed based on the optimal classification feature and the optimal split point. The method further includes determining the optimal classification feature and the optimal split point through the following steps: Determine the number of features for each sample in the training dataset, iterate through all features and extract the possible values ​​of each feature, perform deduplication and calculate the Gini index of each feature after deduplication, divide the dataset into sub-datasets with the largest feature as the split point and calculate the Gini index of the sub-datasets, extract the optimal classification feature based on the Gini index of each feature, and extract the optimal split point based on the Gini index of the sub-datasets.

4. The method according to claim 3, characterized in that, Also includes: The encrypted data is sorted by size and then encrypted using random perturbation.

5. The method according to claim 3, characterized in that, Also includes: When the user inputs data for the first time, the encrypted data is saved.

6. The method according to claim 3, characterized in that, Also includes: When the data input by the user is not the first time, the encrypted data is matched with the encrypted data stored in history.

7. A modeling apparatus for a data encryption model, characterized in that, include: The acquisition module is configured to acquire encrypted training datasets. The extraction module is configured to extract the optimal classification features and optimal split points from the training dataset; The construction module is configured to construct a decision tree based on the optimal classification features and the optimal split point; The training module is configured to train the decision tree using the training dataset through the random forest algorithm to complete the modeling of the data encryption model; The output of the decision tree is represented using a Boolean variable polynomial, and each node in the decision tree corresponds to a Boolean variable. The extraction module is further configured to: determine the number of features for each sample in the training dataset, traverse all features and extract the possible values ​​of each feature, calculate the Gini index of each feature after deduplication, divide the dataset into sub-datasets with the largest feature as the split point and calculate the Gini index of the sub-datasets, extract the optimal classification feature based on the Gini index of each feature, and extract the optimal split point based on the Gini index of the sub-datasets.

8. An electronic device, characterized in that, include: One or more processors; A storage device configured to store one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 6.

Images