WO2020258727A1 - Data encryption method, apparatus and device, and medium - Google Patents

Abstract

Disclosed are a data encryption method, apparatus and device, and a medium, which are used to solve the problems of a relatively high resource consumption and a relatively low efficiency during encryption and obfuscation processing of mass data. The method specifically comprises: acquiring a data set to be encrypted, and encrypting same to obtain a ciphertext data set; determining, according to a set manner, the amount of obfuscation corresponding to the ciphertext data set, and generating obfuscation parameters according to the amount of obfuscation, wherein the amount of obfuscation is less than the amount of ciphertext data in the ciphertext data set; and performing obfuscation processing on the ciphertext data set on the basis of each obfuscation parameter to obtain an obfuscated ciphertext data set. Therefore, a certain amount of obfuscation parameters are generated, and the ciphertext data set is subjected to the obfuscation processing according to each obfuscation parameter, so that the obtained obfuscated ciphertext data set is hard to crack; and furthermore, the number of the generated obfuscation parameters is relatively small, such that the data security is improved, the generation time of the obfuscation parameters is also saved on, and the data processing efficiency is improved.

Description

Data encryption method, device, equipment and medium

Cross references to related applications

This application claims the priority of a Chinese patent application filed with the Chinese Patent Office on June 28, 2019, the application number is 201910580587.0, and the application name is "a data encryption method, device, equipment, and medium", the entire content of which is incorporated by reference In this application.

Technical field

This application relates to the field of data encryption technology, and in particular to a data encryption method, device, equipment and medium.

Background technique

In practical applications, it is usually necessary to encrypt a large amount of data. For example, in a distributed machine learning process, it may be necessary to encrypt a large number of model parameters (such as deep neural network model parameters) generated in the machine learning process.

However, in actual application scenarios, after encrypting a large amount of data to obtain the corresponding ciphertext data, these ciphertext data may also be cracked. How to reduce the risk of cracking the ciphertext data while reducing the processing of large amounts of data The processing resources consumed at the time and the improvement of data processing efficiency are issues that need to be considered.

Summary of the invention

The embodiments of the present application provide a data encryption method, device, equipment, and medium to reduce the risk of cracking ciphertext data, reduce processing resources consumed when processing large amounts of data, and improve data processing efficiency. Yes, the technical solutions provided by the embodiments of this application are as follows:

In the first aspect, an embodiment of the present application provides a data encryption method, including:

Obtain the data set to be encrypted, and encrypt the data set to obtain the ciphertext data set of the data set;

Determine the amount of confusion in the ciphertext data set according to the setting method, and generate confusion parameters according to the amount of confusion, where the amount of confusion is less than the number of ciphertext data in the ciphertext data set;

Based on each confusion parameter, the ciphertext data set is obfuscated to obtain the confused ciphertext data set of the ciphertext data set.

In a possible implementation manner, determining the obfuscation quantity of the ciphertext data set according to the setting method includes:

Obtain the number of ciphertext data in the ciphertext data set;

The product of the setting coefficient and the number of ciphertext data in the ciphertext data set is determined as the confusion quantity corresponding to the ciphertext data set, where the setting coefficient is a value greater than 0 and less than 1.

In a possible implementation manner, determining the obfuscation quantity of the ciphertext data set according to the setting method includes:

Obtain the number of ciphertext data in the ciphertext data set, and generate a random number within a set range, where the set range is greater than 0 and less than 1;

The product of the random number and the number of ciphertext data in the ciphertext data set is determined as the confusion quantity corresponding to the ciphertext data set.

In a possible implementation manner, the ciphertext data set is obfuscated based on each obfuscation parameter to obtain the obfuscated ciphertext data set of the ciphertext data set, including:

For each ciphertext data in the ciphertext data set, randomly select a confusion parameter from each confusion parameter as the confusion parameter of the ciphertext data, and perform the confusion processing on the ciphertext data based on the confusion parameter of the ciphertext data, and obtain Obfuscated ciphertext data of ciphertext data;

Based on the obfuscated ciphertext data of each ciphertext data in the ciphertext data set, the obfuscated ciphertext data set of the ciphertext data set is generated.

In a possible implementation manner, encrypting the data set to obtain the ciphertext data set of the data set includes:

The homomorphic encryption algorithm is used to encrypt the data set to obtain the ciphertext data set of the data set.

In a possible implementation manner, the data set is a multi-dimensional matrix containing various model parameters to be encrypted.

In a possible implementation manner, the homomorphic encryption algorithm includes Paillier algorithm, RSA algorithm, and Gentry algorithm.

In a possible implementation manner, after obtaining the obfuscated ciphertext data set of the ciphertext data set, the method further includes:

Store the obtained obfuscated ciphertext data set.

In a possible implementation manner, the formula for calculating the amount of confusion may be expressed as: N=n*α; where N is the amount of confusion, α is the setting coefficient, and n is the number of ciphertext data.

In the second aspect, an embodiment of the present application provides a data encryption device, including:

The data acquisition unit is used to acquire the data set to be encrypted;

The data encryption unit is used to encrypt the data set to obtain the ciphertext data set of the data set;

The obfuscation generating unit is used to determine the obfuscation quantity of the ciphertext data set according to the setting method, and generate obfuscation parameters according to the obfuscation quantity, where the obfuscation quantity is less than the quantity of ciphertext data in the ciphertext data set;

The obfuscation processing unit is used to perform obfuscation processing on the ciphertext data set based on each obfuscation parameter to obtain the obfuscated ciphertext data set of the ciphertext data set.

In a possible implementation manner, when determining the obfuscation quantity of the ciphertext data set according to the setting method, the obfuscation generating unit is specifically configured to:

Obtain the number of ciphertext data in the ciphertext data set;

The product of the setting coefficient and the number of ciphertext data in the ciphertext data set is determined as the confusion quantity corresponding to the ciphertext data set, where the setting coefficient is a value greater than 0 and less than 1.

In a possible implementation manner, when determining the obfuscation quantity of the ciphertext data set according to the setting method, the obfuscation generating unit is specifically configured to:

Obtain the number of ciphertext data in the ciphertext data set, and generate a random number within a set range, where the set range is greater than 0 and less than 1;

The product of the random number and the number of ciphertext data in the ciphertext data set is determined as the confusion quantity corresponding to the ciphertext data set.

In a possible implementation manner, when obfuscating the ciphertext data set based on each obfuscation parameter to obtain the obfuscated ciphertext data set of the ciphertext data set, the obfuscation processing unit is specifically configured to:

For each ciphertext data in the ciphertext data set, randomly select a confusion parameter from each confusion parameter as the confusion parameter of the ciphertext data, and perform the confusion processing on the ciphertext data based on the confusion parameter of the ciphertext data, and obtain Obfuscated ciphertext data of ciphertext data;

Based on the obfuscated ciphertext data of each ciphertext data in the ciphertext data set, the obfuscated ciphertext data set of the ciphertext data set is generated.

In a possible implementation manner, the data encryption unit is specifically configured to use a homomorphic encryption algorithm to encrypt the data set to obtain the ciphertext data set of the data set.

In a possible implementation manner, the data set is a multi-dimensional matrix containing various model parameters to be encrypted.

In a possible implementation manner, the homomorphic encryption algorithm includes Paillier algorithm, RSA algorithm, and Gentry algorithm.

In a possible implementation manner, the device further includes a storage unit;

The storage unit is used to store the obtained obfuscated ciphertext data set.

In a possible implementation manner, the formula for calculating the amount of confusion may be expressed as: N=n*α; where N is the amount of confusion, α is the setting coefficient, and n is the number of ciphertext data.

In a third aspect, an embodiment of the present application also provides a data encryption device, including: a memory, a processor, and a computer program stored in the memory and running on the processor. The processor executes the computer program to implement the embodiment of the present application. Provide data encryption method.

In a fourth aspect, an embodiment of the present application also provides a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer instructions are executed by a processor to implement the data encryption method provided in the embodiments of the present application.

The beneficial effects of the embodiments of the present application are as follows:

In the embodiment of this application, after encrypting the data set to obtain the ciphertext data set, a certain number of obfuscation parameters are generated, and the ciphertext data set is obfuscated according to each obfuscation parameter, so that the finally obtained obfuscated ciphertext data The collection is difficult to crack, thereby improving data security. Moreover, since the number of generated confusion parameters is small, while improving data security, it also saves the generation time of confusion parameters and improves the data collection. Processing efficiency.

Other features and advantages of the present application will be described in the following description, and partly become obvious from the description, or understood by implementing the present application. The purpose and other advantages of this application can be realized and obtained through the structure specified in the written description, claims, and drawings.

Description of the drawings

The drawings described here are used to provide a further understanding of the application and constitute a part of the application. The exemplary embodiments and descriptions of the application are used to explain the application and do not constitute an improper limitation of the application. In the attached picture:

FIG. 1 is a schematic flowchart of a data encryption method in an embodiment of the application;

FIG. 2 is a schematic diagram of a specific flow of a data encryption method in an embodiment of the application;

3 is a schematic diagram of the functional structure of the data encryption device in an embodiment of the application;

Figure 4 is a schematic diagram of the hardware structure of a data encryption device in an embodiment of the application.

Detailed ways

In order to enable those skilled in the art to better understand this application, firstly, the technical terms mentioned in this application will be explained.

1. Encryption is a data processing technology that uses a special algorithm to change the original data so that even if unauthorized users obtain encrypted data, they still cannot obtain the original data because they do not know the decryption method. The encryption in this application can be but not limited to: homomorphic encryption.

Among them, homomorphic encryption is an encryption method that supports arithmetic operations on ciphertext data. According to the different arithmetic operations supported, homomorphic encryption is divided into the following three types:

Addition homomorphic encryption is the homomorphic encryption that supports addition and subtraction operations. For example, Paillier algorithm is homomorphic for addition and subtraction operations;

Multiplication homomorphic encryption is the homomorphic encryption that supports multiplication and division operations. For example, the RSA algorithm is homomorphic for multiplication and division operations;

Fully homomorphic encryption, in order to support the homomorphic encryption of various operations such as addition, subtraction, multiplication and division, polynomial evaluation, exponents, logarithms, and trigonometric functions, for example, the Gentry algorithm is homomorphic for various operations.

2. The data set to be encrypted is a set of various data to be encrypted, for example, a multi-dimensional matrix containing a large number of model parameters to be encrypted.

3. Obfuscation parameters are parameters used to obfuscate ciphertext data, such as random numbers.

In order to make the purpose, technical solutions and beneficial effects of this application clearer, the following will clearly and completely describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments These are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

At present, in order to further improve data security and reduce the risk of cracking ciphertext data, usually after encrypting the data set to obtain the ciphertext data set, for each ciphertext data in the ciphertext data set, it is the ciphertext data Generate an obfuscation parameter, and perform obfuscation processing on the ciphertext data based on the obfuscation parameter, thereby obtaining the obfuscated ciphertext data of the ciphertext data, and then, according to the obfuscated ciphertext data of each ciphertext data in the ciphertext data set Text data, the obfuscated ciphertext data set of the ciphertext data set can be obtained. Although this obfuscation method can reduce the risk of cracking the ciphertext data set and improve the security of the ciphertext data set, when generating obfuscation parameters, it is necessary to generate a confusion for each ciphertext data in the ciphertext data set. Parameters, causing confusion The generation of parameters requires more calculation time and more processing resources than pure encryption, thereby reducing data processing efficiency and consuming a lot of processing resources. For example, in the application scenario of deep learning, the training process of the deep learning model may require 1 second of processing time. If a large number of model parameters generated in the deep learning process are encrypted, and the current obfuscation method is used to encrypt the large number of If the ciphertext data is obfuscated, it may take 3 hours of processing time to complete the model training, and it will also take up a lot of processing resources.

In order to solve the problems of high resource consumption and low processing efficiency in the current obfuscation method, in the embodiment of the present application, after obtaining the data set to be encrypted, the data set is encrypted to obtain the ciphertext of the data set Data collection; Determine the amount of confusion in the ciphertext data set according to the setting method, and generate confusion parameters according to the amount of confusion, where the amount of confusion is less than the number of ciphertext data in the ciphertext data set; based on each confusion parameter, The ciphertext data set is obfuscated to obtain the confused ciphertext data set of the ciphertext data set. In this way, after the data set is encrypted to obtain the ciphertext data set, a certain number of confusion parameters are generated, and the ciphertext data set is obfuscated according to each confusion parameter, so that the finally obtained confused ciphertext data set is difficult to be deciphered , Thereby improving data security, and because the number of generated obfuscated parameters is small, while improving data security, it also saves the generation time of obfuscated parameters, and improves the processing efficiency of the data set.

After introducing the application scenarios and design ideas of the embodiments of the present application, the technical solutions provided by the embodiments of the present application are described below.

The embodiments of the present application provide a data encryption method, which can be applied to any device that needs to encrypt a large amount of data, such as computers, cloud servers and other devices. Specifically, referring to FIG. 1, the flow of the data encryption method provided by the embodiment of the present application is as follows:

Step 101: Obtain a data set to be encrypted, and encrypt the data set to obtain a ciphertext data set of the data set.

In practical applications, an encryption algorithm can be selected from among encryption algorithms such as Paillier algorithm, RSA algorithm, and Gentry algorithm to encrypt the data set according to actual requirements and device performance, thereby obtaining the ciphertext data set of the data set.

Step 102: Determine the confusion quantity of the ciphertext data set according to the setting method, and generate confusion parameters according to the confusion quantity, wherein the confusion quantity is less than the quantity of ciphertext data in the ciphertext data set.

In specific implementation, when determining the amount of confusion of the ciphertext data set according to the setting method, the following methods can be used but not limited to:

The first method: Obtain the number of ciphertext data in the ciphertext data set, and determine the product of the setting coefficient and the number of ciphertext data in the ciphertext data set as the confusion quantity corresponding to the ciphertext data set, where The coefficient is less than 1.

For example: assuming that the number of ciphertext data in the ciphertext data set is 10 and the set coefficient is 0.5, the product 5 of the number of ciphertext data in the ciphertext data set 10 and the set coefficient 0.5 can be determined as ciphertext data The confusion quantity corresponding to the set, the calculation formula of the confusion quantity can be expressed as: N=n*α;

Among them, N is the amount of confusion, α is the setting coefficient, and n is the number of ciphertext data;

The second method: Get the number of ciphertext data in the ciphertext data set, and generate a random number within the set range, and determine the product of the random number and the number of ciphertext data in the ciphertext data set as the ciphertext data The confusion amount corresponding to the set, where the setting range is (0, 1).

For example: assuming that the number of ciphertext data in the ciphertext data set is 10, and the random number generated according to the set range (0,1) is 0.6, the number of ciphertext data in the ciphertext data set can be 10 and the random number The product 6 of 0.6 is determined as the amount of confusion corresponding to the ciphertext data set.

Further, after the confusion quantity of the ciphertext data set is determined, the confusion parameter can be generated according to the confusion quantity. For example: assuming that the number of confusions in the ciphertext data set is 6, then 6 confusion parameters can be generated.

Step 103: Perform obfuscation processing on the ciphertext data set based on each obfuscation parameter to obtain the obfuscated ciphertext data set of the ciphertext data set.

In the embodiments of the present application, when performing obfuscation processing on the ciphertext data set based on each obfuscation parameter, the following methods can be adopted but not limited to:

First, for each ciphertext data in the ciphertext data set, randomly select a confusion parameter from each confusion parameter as the confusion parameter of the ciphertext data, and based on the confusion parameter of the ciphertext data, the ciphertext data Perform obfuscation processing to obtain obfuscated ciphertext data of the ciphertext data.

Then, based on the obfuscated ciphertext data of each ciphertext data in the ciphertext data set, the obfuscated ciphertext data set of the ciphertext data set is generated.

Finally, the obtained obfuscated ciphertext data set of the ciphertext data set is stored.

For example: assuming that the number of ciphertext data in the ciphertext data set is 10 and the number of confusion parameters is 6, for the 10 ciphertext data, one confusion parameter can be randomly selected from the 6 confusion parameters. Obfuscation parameters of the ciphertext data, the respective obfuscation parameters of the 10 ciphertext data are obtained, and based on the respective obfuscation parameters of the 10 ciphertext data, the 10 ciphertext data are respectively obfuscated to obtain the 10 ciphertext data The respective obfuscated ciphertext data of the data, and further, the obfuscated ciphertext data set of the ciphertext data set can be obtained according to the respective obfuscated ciphertext data of the 10 ciphertext data.

In this way, after the data set is encrypted to obtain the ciphertext data set, a certain number of confusion parameters are generated, and the ciphertext data set is obfuscated according to each confusion parameter, so that the finally obtained confused ciphertext data set is difficult to be deciphered , Thereby improving data security, and because the number of generated obfuscated parameters is small, while improving data security, it also saves the generation time of obfuscated parameters, and improves the processing efficiency of the data set.

The following uses "homomorphic encryption of the data set to be encrypted, and the data set is a multi-dimensional matrix containing each model parameter to be encrypted" as a specific application scenario. The data encryption method provided by the embodiment of the application will be further described in detail, see Figure As shown in 2, the specific process of the data encryption method provided by the embodiment of this application is as follows:

Step 201: Obtain the matrix M to be encrypted.

Step 202: Use the homomorphic encryption algorithm F(M) to perform homomorphic encryption on the matrix M to obtain the homomorphic ciphertext matrix [[M]] of the matrix M.

Step 203: Determine the number of homomorphic ciphertext parameters in the homomorphic ciphertext matrix [[M]] as 100, and set the number of homomorphic ciphertext parameters in the homomorphic ciphertext matrix [[M]] to 100 and the set coefficient The product 60 of 0.6 is determined as the confusion amount of the homomorphic ciphertext matrix [[M]].

Step 204: According to the confusion number 60 of the homomorphic ciphertext matrix [[M]], 60 confusion parameters are generated.

Step 205: Regarding the 100 homomorphic ciphertext parameters in the homomorphic ciphertext matrix [[M]], a confusion parameter is randomly selected from the 60 confusion parameters as the confusion parameter of the homomorphic ciphertext parameter to obtain the Obfuscation parameters for each of the 100 homomorphic ciphertext parameters.

Step 206: Based on the respective obfuscation parameters of the 100 homomorphic ciphertext parameters, perform obfuscation processing on the 100 homomorphic ciphertext parameters respectively to obtain the respective obfuscated homomorphic ciphertext parameters of the 100 homomorphic ciphertext parameters.

Step 207: Obtain the confused homomorphic ciphertext matrix [[M]]' of the homomorphic ciphertext matrix [[M]] according to the respective confused homomorphic ciphertext parameters of the 100 homomorphic ciphertext parameters.

Based on the foregoing embodiment, an embodiment of the present application provides a data encryption device. As shown in FIG. 3, the data encryption device 300 provided by the embodiment of the present application at least includes:

The data obtaining unit 301 is configured to obtain a data set to be encrypted;

The data encryption unit 302 is configured to encrypt the data set to obtain the ciphertext data set of the data set;

The obfuscation generating unit 303 is used to determine the obfuscation quantity of the ciphertext data set according to the setting method, and generate obfuscation parameters according to the obfuscation quantity, where the obfuscation quantity is less than the quantity of ciphertext data in the ciphertext data set;

The obfuscation processing unit 304 is configured to perform obfuscation processing on the ciphertext data set based on each obfuscation parameter to obtain the obfuscated ciphertext data set of the ciphertext data set.

In a possible implementation manner, when determining the amount of confusion in the ciphertext data set according to the setting method, the confusion generating unit 303 is specifically configured to:

Obtain the number of ciphertext data in the ciphertext data set;

The product of the setting coefficient and the number of ciphertext data in the ciphertext data set is determined as the confusion quantity corresponding to the ciphertext data set, where the setting coefficient is a value greater than 0 and less than 1.

In a possible implementation manner, when determining the amount of confusion in the ciphertext data set according to the setting method, the confusion generating unit 303 is specifically configured to:

Obtain the number of ciphertext data in the ciphertext data set, and generate a random number within a set range, where the set range is greater than 0 and less than 1;

The product of the random number and the number of ciphertext data in the ciphertext data set is determined as the confusion quantity corresponding to the ciphertext data set.

In a possible implementation manner, when obfuscating the ciphertext data set based on each obfuscation parameter to obtain the obfuscated ciphertext data set of the ciphertext data set, the obfuscation processing unit 304 is specifically configured to:

For each ciphertext data in the ciphertext data set, randomly select a confusion parameter from each confusion parameter as the confusion parameter of the ciphertext data, and perform the confusion processing on the ciphertext data based on the confusion parameter of the ciphertext data, and obtain Obfuscated ciphertext data of ciphertext data;

Based on the obfuscated ciphertext data of each ciphertext data in the ciphertext data set, the obfuscated ciphertext data set of the ciphertext data set is generated.

In a possible implementation manner, the data encryption unit 302 is specifically configured to use a homomorphic encryption algorithm to encrypt the data set to obtain the ciphertext data set of the data set.

In a possible implementation manner, the data set is a multi-dimensional matrix containing various model parameters to be encrypted.

In a possible implementation manner, the homomorphic encryption algorithm includes Paillier algorithm, RSA algorithm, and Gentry algorithm.

In a possible implementation manner, the device further includes a storage unit 305;

The storage unit 305 is configured to store the obtained obfuscated ciphertext data set.

In a possible implementation manner, the formula for calculating the amount of confusion may be expressed as: N=n*α; where N is the amount of confusion, α is the setting coefficient, and n is the number of ciphertext data.

It should be noted that the principle of solving the technical problems of the data encryption device 300 provided by the embodiment of the application is similar to the data encryption method provided by the embodiment of the application. Therefore, the implementation of the data encryption device 300 provided by the embodiment of the application can refer to this application. The implementation of the data encryption method provided in the embodiment will not be repeated here.

After introducing the data encryption method and device provided in the embodiment of the present application, next, the data encryption device provided in the embodiment of the present application will be briefly introduced.

4, the data encryption device 400 provided by the embodiment of the present application at least includes: a processor 41, a memory 42, and a computer program stored on the memory 42 and running on the processor 41. When the processor 41 executes the computer program Implement the data encryption method provided in the embodiment of this application.

It should be noted that the data encryption device 400 shown in FIG. 4 is only an example, and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

The data encryption device 400 provided by the embodiment of the present application may further include a bus 43 connecting different components (including the processor 41 and the memory 42). Wherein, the bus 43 represents one or more of several types of bus structures, including a memory bus, a peripheral bus, and a local bus.

The memory 42 may include a readable medium in the form of a volatile memory, such as a random access memory (RAM) 421 and/or a cache memory 422, and may further include a read only memory (ROM) 423.

The memory 42 may also include a program tool 425 having a set of (at least one) program modules 424. The program modules 424 include, but are not limited to, an operating subsystem, one or more application programs, other program modules, and program data. In these examples, Each one or some combination may include the realization of the network environment.

The data encryption device 400 may also communicate with one or more external devices 44 (such as keyboards, remote controls, etc.), and may also communicate with one or more devices (such as mobile phones, computers, etc.) that enable users to interact with the data encryption device 400. , And/or, communicate with any device (such as a router, modem, etc.) that enables the data encryption device 400 to communicate with one or more other data encryption devices 400. This communication can be performed through an input/output (Input/Output, I/O) interface 45. In addition, the data encryption device 400 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet) through the network adapter 46. As shown in FIG. 4, the network adapter 46 communicates with other modules of the data encryption device 400 through the bus 43. It should be understood that although not shown in FIG. 4, other hardware and/or software modules can be used in conjunction with the data encryption device 400, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, disk arrays ( Redundant Arrays of Independent Disks, RAID) subsystems, tape drives, and data backup storage subsystems.

In addition, the embodiments of the present application also provide a computer-readable storage medium that stores computer instructions, and when the computer instructions are executed by a processor, the data encryption method provided in the embodiments of the present application is implemented. Specifically, the executable program may be built into the data encryption device 400, so that the data encryption device 400 can implement the data encryption method provided by the embodiment of the present application by executing the built-in executable program.

In addition, the data encryption method provided in the embodiments of the present application can also be implemented as a program product. The program product includes program code. When the program product can run on the data encryption device 400, the program code is used to enable the data encryption device 400 executes the data encryption method provided in the embodiment of the present application.

The program product provided in the embodiments of the present application may use any combination of one or more readable media, where the readable medium may be a readable signal medium or a readable storage medium, and the readable storage medium may be, but is not limited to, an electronic , Magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. Specifically, more specific examples (non-exhaustive list) of readable storage media include: having one or more Electrical connection of wires, portable disk, hard disk, RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), optical fiber, portable compact disk Read-Only Memory (Compact Disc Read-Only Memory, CD- ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

The program product provided by the embodiments of the present application can adopt a CD-ROM and include program code, and can also run on a computing device. However, the program products provided by the embodiments of the present application are not limited thereto. In the embodiments of the present application, the readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, device, or device. In conjunction with.

It should be noted that although several units or subunits of the device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of a unit described above can be further divided into multiple units to be embodied.

In addition, although the operations of the method of the present application are described in a specific order in the drawings, this does not require or imply that these operations must be performed in the specific order, or that all the operations shown must be performed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and/or one step may be decomposed into multiple steps for execution.

Those skilled in the art should understand that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware.

Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. In this way, if these modifications and variations of the embodiments of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these modifications and variations.

Claims (20)

A data encryption method, characterized in that it comprises: Obtaining a data set to be encrypted, and encrypting the data set to obtain a ciphertext data set of the data set; Determine the confusion quantity of the ciphertext data set according to the setting method, and generate confusion parameters according to the confusion quantity, wherein the confusion quantity is less than the quantity of ciphertext data in the ciphertext data set; Based on each confusion parameter, perform confusion processing on the ciphertext data set to obtain the confused ciphertext data set of the ciphertext data set. The data encryption method according to claim 1, wherein determining the amount of confusion of the ciphertext data set according to a setting method comprises: Acquiring the number of ciphertext data in the ciphertext data set; The product of the setting coefficient and the number of ciphertext data in the ciphertext data set is determined as the confusion quantity corresponding to the ciphertext data set, where the setting coefficient is a value greater than 0 and less than 1. The data encryption method according to claim 1, wherein determining the amount of confusion of the ciphertext data set according to a setting method comprises: Acquire the number of ciphertext data in the ciphertext data set, and generate a random number within a set range, where the set range is greater than 0 and less than 1; The product of the random number and the number of ciphertext data in the ciphertext data set is determined as the confusion quantity corresponding to the ciphertext data set. The data encryption method according to any one of claims 1 to 3, wherein the ciphertext data set is obfuscated based on each obfuscation parameter to obtain the obfuscated ciphertext data set of the ciphertext data set, include: For each ciphertext data in the ciphertext data set, randomly select a confusion parameter from the various confusion parameters as the confusion parameter of the ciphertext data, and based on the confusion parameter of the ciphertext data, Performing obfuscation processing on the ciphertext data to obtain obfuscated ciphertext data of the ciphertext data; Based on the obfuscated ciphertext data of each ciphertext data in the ciphertext data set, the obfuscated ciphertext data set of the ciphertext data set is generated. The data encryption method according to claim 1, wherein encrypting the data set to obtain the ciphertext data set of the data set comprises: The homomorphic encryption algorithm is used to encrypt the data set to obtain the ciphertext data set of the data set. The data encryption method according to claim 1, wherein the data set is a multi-dimensional matrix containing various model parameters to be encrypted. The data encryption method according to claim 5 or 6, characterized in that: The homomorphic encryption algorithm includes Paillier algorithm, RSA algorithm and Gentry algorithm. 3. The data encryption method according to claim 1, wherein after obtaining the obfuscated ciphertext data set of the ciphertext data set, the method further comprises: Store the obtained obfuscated ciphertext data set. The data encryption method according to claim 2, wherein the calculation formula for the amount of confusion can be expressed as: N=n*α; Among them, N is the amount of confusion, α is the set coefficient, and n is the number of ciphertext data. A data encryption device, characterized in that it comprises: The data acquisition unit is used to acquire the data set to be encrypted; A data encryption unit, configured to encrypt the data set to obtain a ciphertext data set of the data set; The confusion generating unit is configured to determine the confusion quantity of the ciphertext data set according to a setting method, and generate confusion parameters according to the confusion quantity, wherein the confusion quantity is less than the quantity of ciphertext data in the ciphertext data set ； The obfuscation processing unit is configured to perform obfuscation processing on the ciphertext data set based on each obfuscation parameter to obtain the obfuscated ciphertext data set of the ciphertext data set. 10. The data encryption device according to claim 10, wherein when determining the amount of confusion of the ciphertext data set according to a setting method, the confusion generating unit is configured to: Acquiring the number of ciphertext data in the ciphertext data set; The product of the setting coefficient and the number of ciphertext data in the ciphertext data set is determined as the confusion quantity corresponding to the ciphertext data set, where the setting coefficient is a value greater than 0 and less than 1. The data encryption device according to claim 10, wherein when determining the amount of confusion of the ciphertext data set according to a setting method, the confusion generating unit is configured to: Acquire the number of ciphertext data in the ciphertext data set, and generate a random number within a set range, where the set range is greater than 0 and less than 1; The product of the random number and the number of ciphertext data in the ciphertext data set is determined as the confusion quantity corresponding to the ciphertext data set. The data encryption device according to any one of claims 10-12, wherein the obfuscated ciphertext data set of the ciphertext data set is obtained by performing obfuscation processing on the ciphertext data set based on each obfuscation parameter When, the obfuscation processing unit is used to: For each ciphertext data in the ciphertext data set, randomly select a confusion parameter from the various confusion parameters as the confusion parameter of the ciphertext data, and based on the confusion parameter of the ciphertext data, Performing obfuscation processing on the ciphertext data to obtain obfuscated ciphertext data of the ciphertext data; Based on the obfuscated ciphertext data of each ciphertext data in the ciphertext data set, the obfuscated ciphertext data set of the ciphertext data set is generated. The data encryption device according to claim 10, wherein: The data encryption unit is specifically configured to use a homomorphic encryption algorithm to encrypt the data set to obtain the ciphertext data set of the data set. 9. The data encryption device of claim 10, wherein the data set is a multi-dimensional matrix containing each model parameter to be encrypted. The data encryption method according to claim 10 or 11, wherein: The homomorphic encryption algorithm includes Paillier algorithm, RSA algorithm and Gentry algorithm. The data encryption device according to claim 10, wherein the device further comprises a storage unit; The storage unit is used to store the obtained obfuscated ciphertext data set. The data encryption device according to claim 11, wherein the calculation formula for the amount of confusion can be expressed as: N=n*α; Among them, N is the amount of confusion, α is the set coefficient, and n is the number of ciphertext data. A data encryption device, characterized in that it comprises: a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program when the computer program is executed. Implement the data encryption method according to any one of claims 1-9. A computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions, which when executed by a processor implement the data encryption method according to any one of claims 1-9.

Images