WO2024239593A1 - Hybrid federated logistic regression method based on homomorphic encryption - Google Patents

Abstract

The present invention relates to the technical field of computers, and provides a hybrid federated logistic regression method based on homomorphic encryption. The method comprises: performing module segmentation on data to form data data1 and data data2; performing longitudinal federated logistic regression training on the data data1 and the data data2; for the data data1 and the data data2, using a random number r as a seed to generate a homomorphic public-private key pair; encrypting w1, intercept1, w2, and intercept2, and performing security aggregation on encrypted parameters; and sending an aggregation intermediate result parameter to each participant, so that each participant decrypts the aggregation intermediate result parameter, and performs parameter iteration until a requirement is met to obtain a final training model. The bottleneck of modeling and intercommunication of internal and external data of a single institution is effectively broken through, local data does not leave a database, and federated learning model training can be performed in combination with multi-party data, thereby improving the accuracy of a federated learning model.

Description

A hybrid federated logistic regression method based on homomorphic encryption Technical Field

The present invention relates to the field of computer technology, and in particular to a hybrid federated logistic regression method based on homomorphic encryption.

Background Art

Privacy computing is known as Privacy Compute, which refers to a collection of technologies that implement data analysis and computing while protecting the data from external leakage. Compared with traditional data usage methods, the encryption mechanism of privacy computing can enhance data protection and reduce the risk of data leakage. Therefore, it is regarded as a way to achieve "data minimization". At the same time, traditional data security methods, such as data desensitization or anonymization, all sacrifice some data dimensions, resulting in the inability to effectively use data information. Privacy computing provides another solution to ensure that the value of data is maximized as much as possible under the premise of security.

The full name of multi-party secure computing is Secure Multi-Party Computation, generally abbreviated as MPC, which refers to the realization of data fusion computing among multiple parties under the premise of protecting data security and privacy. In a network environment, participants in a task each have their own data, and multiple participants calculate a certain function in a distributed manner through a communication protocol to complete the computing task. Each participant provides their own input for the computing function, and the participants obtain the correct output of the function. At the same time, this process protects the user's privacy data, that is, in addition to obtaining the output they deserve, participants cannot obtain any input information from other users. Secure multi-party computing can realize user data sharing under privacy protection, which is of great significance for the effective use of data. In particular, laws related to information security stipulate strict user data protection requirements, and the traditional method of direct data sharing can no longer meet the requirements.

Traditional secure multi-party computing is implemented through complex interactive cryptographic protocols. Participants encrypt their input data and pass it to other participants according to the protocol. Participants obtain the output of the original computing task through a series of calculations and conversions on the ciphertext. In this process, since participants cannot directly perform calculations on the original data, their computing efficiency and computing functions will be greatly limited. Secure multi-party computing implemented through traditional secure multi-party computing protocols must directly make a trade-off between computing functions and computing efficiency. The first type only supports specific relatively simple computing functions and does not support complex or flexible computing tasks. The second type supports general computing tasks, but due to its low efficiency, it only supports the calculation of a small amount of data.

Federated learning is called Federated Learning (FL for short), also known as federated machine learning. Federated learning is to complete multi-party joint machine learning training by circulating and processing intermediate encrypted data without leaving the local original data. According to the different distribution of data involved in the calculation among data parties, it can be divided into horizontal federated learning, vertical federated learning and federated transfer learning. Among them, horizontal federated learning means that the data of different participants have a large overlap of features, but the overlap of data samples, that is, the samples to which the features belong, is not high. Vertical federated learning means that the data samples of different participants have a large overlap, but the overlap of sample features is not high. At present, horizontal federated learning and vertical federated learning have been implemented in many scenarios and have been applied. At the same time, as more and more application scenarios emerge, there are situations where horizontal federated learning and vertical federated learning need to be used simultaneously to meet the needs. Based on the current one-way federated learning, when facing a mixed data segmentation scenario (data includes both horizontal segmentation and vertical segmentation, for example, A and B have the same samples but different features, and C and D have the same features but different samples), it is necessary to build multiple federated learning models through multiple stages. To achieve horizontal federated learning and vertical federated learning respectively, the demand can be met. However, the operation steps in this way are relatively cumbersome, the amount of data interaction is usually large, and it takes up more network resources and computing resources, which is not only time-consuming and labor-intensive, but also affects efficiency.

Summary of the invention

The purpose of the present invention is to provide a hybrid federated logistic regression method based on homomorphic encryption, which can use the distributed hybrid federated machine learning technology with privacy protection, utilize the data of multiple institutions in the same industry and different institutions in different industries, effectively break through the bottleneck of internal and external data modeling intercommunication of a single institution, and realize that local data is not stored out of the warehouse, but can be combined with multi-party data for federated learning model training, so that all participants can achieve equal and mutually beneficial joint modeling, so as to improve the accuracy of the federated learning model.

The embodiment of the present invention is achieved as follows:

In a first aspect, an embodiment of the present application provides a hybrid federated logistic regression method based on homomorphic encryption, which comprises the following steps:

The data of the first data cube is divided into modules to obtain a first data block and a second data block, and the first data block and the second data cube form data data1, and the second data block and the third data cube form data data2;

Perform longitudinal federated logistic regression training on data data1, merge the parameters to get w1, intercept1 and loss1, perform longitudinal federated logistic regression training on data data2, merge the parameters to get w2, intercept2 and loss2;

According to the merge parameters, perform horizontal federated logistic regression calculations on data1 and data2 respectively;

For data data1 or data data2, each participant calls the key exchange protocol to obtain the same random number r, and uses the random number r as a seed to generate a homomorphic public and private key pair;

According to the aggregation interval parameter, encrypt w1 and intercept1, and encrypt w2 and intercept2 at the same time to obtain the encryption parameters, and send the encrypted parameters to the collaborating party for secure aggregation to obtain the aggregation intermediate result parameters;

The collaborating party sends the aggregated intermediate result parameters to each participating party. Each participating party decrypts the aggregated intermediate result parameters and performs the next round of parameter iteration based on the decrypted aggregated intermediate result parameters until the requirements are met and the final training model is obtained.

In some embodiments of the present invention, the step of performing longitudinal federated logistic regression training on the data data1 includes:

Based on the homomorphic encryption algorithm, the first data block generates a homomorphic encryption public key, and sends the homomorphic encryption public key to the second data party, and the second data party receives the homomorphic encryption public key;

The first data block and the second data block each have initial values of fitting parameters, where the first data block initializes weight wa1 and bias intercept1, and the second data block initializes weight wb;

The first data block calculates the dot product of the feature and the parameter to obtain ua1, and the second data block calculates the dot product of the feature and the parameter to obtain ub;

The second data party transmits ub to the first data block, and the first data block receives ub, and uses the formula ue1=ua1+ub to calculate the total fitting value ue1, and based on the total fitting value ue1 and the true value, uses the loss function to calculate the total loss loss1:

The first data block calculates the gradient factor gdf based on the total fitting value ue1 and the true value, and encrypts the gradient factor gdf to obtain the encrypted gdf;

The first data block sends the encrypted gdf to the second data party, and the second data party calculates the corresponding encrypted gradient gdhb based on the encrypted gdf;

Based on the homomorphic encryption algorithm, the second data party generates a random number Rb and encrypts Rb to obtain encrypted Rb. The second data party sends the sum of the encrypted gradient gdhb and the encrypted Rb to the first data block;

The first data block decrypts the sum into gdhd=gdhb+Rb, and sends gdhd to the second data party;

The second data party receives gdhd, calculates the gradient gdhb according to the formula gdhb=gdhd-Rb, and updates the weight wb according to the gradient gdhb;

The first data block obtains the gradient gdha1 by multiplying the feature and gdf matrix, and updates the weight wa1 and bias intercept1 according to the gradient gdha1.

In some embodiments of the present invention, the step of calculating the gradient factor gdf based on the total fitting value ue1 and the true value of the first data block includes:

The gradient factor gdf is calculated using the formula gdf=xwT-y, where xwT represents the fitting value and y represents the true value.

In some embodiments of the present invention, the step of calculating the corresponding encrypted gradient gdhb according to the encrypted gdf by the second data cube includes:

The encrypted gradient gdhb is calculated according to the formula encrypted gradient gdhb=gradient factor gdf*Xb, where Xb represents the feature column matrix.

In some embodiments of the present invention, the step of performing longitudinal federated logistic regression training on the data data2 includes:

Based on the homomorphic encryption algorithm, the second data block sends the homomorphic encryption public key to the third data party, and the third data party receives the homomorphic encryption public key;

The second data block and the third data block each fit the initial values of the parameters, where the second data block initializes the weight wa2 and the bias intercept2, and the third data block initializes the weight wc;

The second data block calculates the dot product of the feature and the parameter to obtain ua2, and the third data block calculates the dot product of the feature and the parameter to obtain uc;

The third data party transmits uc to the second data block, and the second data block receives uc, calculates the total fitting value ue2 using the formula ue2=ua2+uc, and calculates the total loss loss2 based on the total fitting value ue2 and the true value using the loss function;

The second data block calculates the gradient factor gdf based on the total fitting value ue2 and the true value, and encrypts the gradient factor gdf to obtain the encrypted gdf;

The second data block sends the encrypted gdf to the third data party, and the third data party calculates the encrypted gradient gdhc based on the encrypted gdf;

Based on the homomorphic encryption algorithm, the third data party generates a random number Rc and encrypts Rc to obtain an encrypted Rb. The third data party sends the sum of the encrypted gradient gdhc and the encrypted Rc to the second data block;

The second data block decrypts the sum of the encrypted gradient gdhc and the encrypted Rc into gdhd=gdhc+Rc, and sends gdhd to the third data party;

The third data party receives and updates the weight wc according to gdhd minus the random number Rc;

The second data block obtains the gradient gdha2 by multiplying the feature and gdf matrix, and updates the weight wa2 and bias intercept2 according to the gradient gdha2.

In a second aspect, an embodiment of the present application provides an electronic device, comprising a memory for storing one or more programs and a processor. When the one or more programs are executed by the processor, any method in the first aspect is implemented.

In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a method as described in any one of the first aspects above.

Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

The present invention proposes a hybrid federated logistic regression method based on homomorphic encryption, which includes the following steps: performing module segmentation on the data of the first data party to obtain a first data block and a second data block, and forming data data1 from the first data block and the second data party, and forming data data2 from the second data block and the third data party. Performing longitudinal federated logistic regression training on data data1, merging parameters to obtain w1, intercept1 and loss1, and performing longitudinal federated logistic regression training on data data2, merging parameters to obtain w2, intercept2 and loss2. According to the merged parameters, performing horizontal federated logistic regression calculations on data data1 and data data2 respectively. For data data1 or data data2, each participant calls a key exchange protocol to obtain the same random number r, and uses the random number r as a seed to generate a homomorphic public-private key pair. According to the aggregation interval parameter, encrypt w1 and intercept1, and encrypt w2 and intercept2 at the same time to obtain encryption parameters, and send the encryption parameters to the collaborating party for secure aggregation to obtain aggregation intermediate result parameters. The collaborating party sends the aggregated intermediate result parameters to each participant, and each participant decrypts the aggregated intermediate result parameters and performs the next round of parameter iteration according to the decrypted aggregated intermediate result parameters until the requirements are met and the final training model is obtained. The hybrid federated logistic regression model training process in the final hybrid data segmentation scenario is realized. It solves the scenario where both horizontal federated learning and vertical federated learning are needed to meet the requirements, while improving the computing efficiency. It simplifies the operation process, avoids excessive data interaction, and reduces the use of network resources and computing resources. At the same time, it breaks through the computing limitations of real-life scenarios with large amounts of data, solves the problem that the parties cannot calculate locally, and can also complete the training of the federated learning model to achieve the internal and external data modeling tasks of a single institution. It also realizes the secure multi-party computing of any computing function, breaks through the boundary of centralized local modeling in traditional machine learning, and performs distributed federated machine learning modeling. The current distributed hybrid federated logistic regression algorithm is mainly used in data mixed segmentation scenarios where both horizontal federated learning and vertical federated learning are needed to meet the requirements. It solves the problem that when facing data mixed segmentation scenarios, one-way federated learning needs to build multiple federated learning models through multiple stages to achieve horizontal federated learning and vertical federated learning respectively to meet the requirements. It effectively breaks through the bottleneck of data modeling intercommunication within and outside a single institution, and achieves the goal of not leaving the local data warehouse, but combining data from multiple parties to train federated learning models, allowing all participants to conduct equal and mutually beneficial joint modeling to improve the accuracy of the federated learning model.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

FIG1 is a flow chart of a hybrid federated logistic regression method based on homomorphic encryption provided by an embodiment of the present invention;

FIG2 is a schematic diagram of data segmentation provided by an embodiment of the present invention;

FIG3 is a flowchart of an interaction between a first data block and a second data block provided by an embodiment of the present invention;

FIG4 is a flow chart of interaction between a second data block and a third data party provided by an embodiment of the present invention;

FIG5 is a flowchart of a horizontal federation provided by an embodiment of the present invention;

FIG6 is a schematic structural block diagram of an electronic device provided by an embodiment of the present invention.

Icon: 101 - memory; 102 - processor; 103 - communication interface.

DETAILED DESCRIPTION

In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

Example

Please refer to Figure 1, which is a flow chart of a hybrid federated logistic regression method based on homomorphic encryption provided by an embodiment of the present invention. The present application embodiment provides a hybrid federated logistic regression method based on homomorphic encryption, which includes the following steps:

S110: Divide the data of the first data block into modules to obtain a first data block and a second data block, and form data data1 from the first data block and the second data block, and form data data2 from the second data block and the third data block;

For example, please refer to Figure 2, which is a schematic diagram of data segmentation provided by an embodiment of the present invention. Taking the data of parties A, B, and C as an example, party A contains a label, and the data is first segmented into modules. Data data1 is composed of data blocks A1 and B of A, and data data2 is composed of data blocks A2 and C of A.

S120: Perform longitudinal federated logistic regression training on data data1, merge parameters to obtain w1, intercept1 and loss1, and perform longitudinal federated logistic regression training on data data2, merge parameters to obtain w2, intercept2 and loss2;

Exemplarily, longitudinal federated logistic regression training is performed on data data1 and data data2 respectively, that is, A1 and B are longitudinally federated, and A2 and C are longitudinally federated.

S130: performing horizontal federated logistic regression calculations on data data1 and data data2 respectively according to the merge parameters;

For example, please refer to FIG. 5 , which is a flowchart of a horizontal federation provided by an embodiment of the present invention. Parameter merging: Party A1 and Party B merge parameters to obtain w1, intercept1, and loss 1. Party A2 and Party C merge parameters to obtain w2, intercept2, and loss2. According to the merged parameters, a horizontal federation logistic regression calculation is performed on data1 and data2.

S140: For data data1 or data data2, each participant calls the key exchange protocol to obtain the same random number r, and uses the random number r as a seed to generate a homomorphic public-private key pair;

Specifically, in the horizontal federation part, taking Party 1, Party 2, and Arbiter as an example, each participating party calls the key exchange protocol, obtains the same random number r, and uses the random number as a seed to generate a homomorphic public and private key pair.

S150: Encrypt w1 and intercept1 according to the aggregation interval parameter, and encrypt w2 and intercept2 at the same time to obtain encryption parameters, and send the encryption parameters to the collaborating party for secure aggregation to obtain aggregation intermediate result parameters;

Specifically, each participant encrypts [w1] and [intercept1] according to the aggregation interval parameter, and Party 1 encrypts [w2] and [intercept2], and Party 2 encrypts [w2] and [intercept2], and sends the encrypted parameters to the collaborating parties for secure aggregation.

S160: The collaborating party sends the aggregated intermediate result parameters to each participating party, and each participating party decrypts the aggregated intermediate result parameters and performs the next round of parameter iteration according to the decrypted aggregated intermediate result parameters until the requirements are met to obtain the final training model.

Specifically, the collaborating party sends the aggregated intermediate results [w] and [intercept] to each participating party, and each participating party decrypts to obtain w and intercept, and performs the next round of parameter iteration based on the aggregated and decrypted parameters w and intercept. The final training model can be obtained when the requirements are met.

In the above implementation process, this method uses homomorphic encryption to further increase data security. First, the data is divided into multiple vertical blocks, and then the vertical data blocks are vertically logically back-linked. The model training is carried out, and the horizontal federated logistic regression model training is carried out for multiple vertical data. The training process of the hybrid federated logistic regression model in the final mixed data segmentation scenario is realized. The scenario that requires the use of both horizontal federated learning and vertical federated learning to meet the needs is solved, while improving the computing efficiency. The operation step process is simplified to avoid excessive data interaction and reduce the use of network resources and computing resources. At the same time, it breaks through the computing limitations of real-life scenarios with large amounts of data, solves the problem that the parties cannot calculate locally and store data, and can also complete the training of the federated learning model to achieve the internal and external data modeling tasks of a single institution. It also realizes the secure multi-party computing of any computing function, breaks through the boundary of centralized local modeling in traditional machine learning, and performs distributed federated machine learning modeling. The current distributed hybrid federated logistic regression algorithm is mainly used in data mixed segmentation scenarios that require the use of both horizontal federated learning and vertical federated learning to meet the needs. It solves the problem that when facing data mixed segmentation scenarios, one-way federated learning needs to build multiple federated learning models through multiple stages to achieve horizontal federated learning and vertical federated learning respectively to meet the needs. It effectively breaks through the bottleneck of data modeling intercommunication within and outside a single institution, and achieves the goal of not leaving the local data warehouse, but combining data from multiple parties to train federated learning models, allowing all participants to conduct equal and mutually beneficial joint modeling to improve the accuracy of the federated learning model.

Exemplarily, this method can be applied to operators and commercial banks to solve the communication + financial anti-fraud scenario to realize the feasibility of implementing the data mixed segmentation scenario for federated model training. The types of commercial business almost overlap, and the data dimensions are basically the same. If only the data of one bank is used, it will inevitably cause the sample distribution to be relatively single, and it will not be possible to identify fraudulent behavior using other bank products well. If the user behavior data of multiple commercial banks and telecom operators are combined, the user group will be enriched to a great extent, but the user data of each commercial bank and the communication data of the telecom operator are all private data of the user. Without the permission of the user and the regulatory agency, it is impossible to flow directly to a third party institution to realize data sharing. At this time, the telecom operator has a full amount of samples and some features, and other participants such as commercial banks have the same features (different from the features of the operator), but each has some samples. In the face of this mixed data segmentation scenario, if the hybrid federation idea based on homomorphic encryption proposed by the present invention is adopted, the data of all parties can be easily utilized to realize the data mixed segmentation scenario for federal model training. Among them, each platform node authorizes each other and uploads local resources at the same time. The task creator obtains the data set resources of each participating node, locks the selected resources, initiates the hybrid federated logistic regression algorithm calculation task, and each node collaborates to calculate and realize the calculation process of the hybrid federated logistic regression algorithm, thereby realizing the joint modeling and training task of multi-party data.

In some implementations of this embodiment, the step of performing longitudinal federated logistic regression training on the data data1 includes:

Based on the homomorphic encryption algorithm, the first data block generates a homomorphic encryption public key, and sends the homomorphic encryption public key to the second data party, and the second data party receives the homomorphic encryption public key;

The first data block and the second data block each have initial values of fitting parameters, where the first data block initializes weight wa1 and bias intercept1, and the second data block initializes weight wb;

The first data block calculates the dot product of the feature and the parameter to obtain ua1, and the second data block calculates the dot product of the feature and the parameter to obtain ub;

The second data party transmits ub to the first data block, and the first data block receives ub, and uses the formula ue1=ua1+ub to calculate the total fitting value ue1, and based on the total fitting value ue1 and the true value, uses the loss function to calculate the total loss loss1:

The first data block calculates the gradient factor gdf based on the total fitting value ue1 and the true value, and encrypts the gradient factor gdf to obtain the encrypted gdf;

The first data block sends the encrypted gdf to the second data party, and the second data party calculates the corresponding encrypted gradient gdhb based on the encrypted gdf;

Based on the homomorphic encryption algorithm, the second data party generates a random number Rb and encrypts Rb to obtain encrypted Rb. The second data party sends the sum of the encrypted gradient gdhb and the encrypted Rb to the first data block;

The first data block decrypts the sum into gdhd=gdhd+Rb, and sends gdhd to the second data party;

The second data party receives gdhd, calculates the gradient gdhb according to the formula gdhd=gdhd-Rb, and updates the weight wb according to the gradient gdhb;

The first data block obtains the gradient gdha1 by multiplying the feature and gdf matrix, and updates the weight wa1 and bias intercept1 according to the gradient gdha1.

Exemplarily, please refer to Figure 3, which shows an interaction flow chart of a first data block and a second data block provided by an embodiment of the present invention. The specific process of A1 and B performing vertical federation is as follows: A1 sends the homomorphic encryption public key to B. A1 and B each fit the initial values of the parameters, where A1 initializes the weight wa1 and the bias intercept1; B initializes the weight wb. A1 and B each calculate the dot product of the features and parameters. B transmits the dot product result ub of the features and parameters to A1, and A1 calculates the total fitting value ue 1 of A 1 and B. The total loss is calculated using the loss function based on the total fitting value and the true value: A1 calculates the gradient factor based on the total fitting value and the true value at the same time: gdf = xwT-y = y`-y. A1 sends the encrypted [gdf] to B, and B calculates B's encrypted gradient [gdhb] based on the encrypted [gdf]. Gradient = (feature column) matrix multiplication (gradient factor). B generates a random number and encrypts it [Rb]. Then B sums the encrypted gradient and the encrypted random number [gdhb] + [Rb] and sends it to A1. A1 decrypts the encrypted gradient and the sum of the encrypted random number to gdhd = gdhb + Rb, and A1 sends gdhd to B. A1 obtains A1's gradient gdha1 by multiplying the feature and gdf matrix. A1 updates A1's weights wa1 and intercept1 based on gdha1. B updates B's weight wb based on gdhd minus the added random number Rb, thus completing a round of vertical federated parameter update.

In some implementations of this embodiment, the step of calculating the gradient factor gdf based on the total fitting value ue1 and the true value of the first data block includes:

The gradient factor gdf is calculated using the formula gdf=xwT-y, where xwT represents the fitting value and y represents the true value.

In some implementations of this embodiment, the step of the second data cube calculating the corresponding encrypted gradient gdhb according to the encrypted gdf includes:

The encrypted gradient gdhb is calculated according to the formula encrypted gradient gdhb=gradient factor gdf*Xb, where Xb represents the feature column matrix.

In some implementations of this embodiment, the step of performing longitudinal federated logistic regression training on the data data2 includes:

Based on the homomorphic encryption algorithm, the second data block sends the homomorphic encryption public key to the third data party, and the third data party receives the homomorphic encryption public key;

The second data block and the third data block each fit the initial values of the parameters, where the second data block initializes the weight wa2 and the bias intercept2, and the third data block initializes the weight wc;

The second data block calculates the dot product of the feature and the parameter to obtain ua2, and the third data block calculates the dot product of the feature and the parameter to obtain uc;

The third data party transmits uc to the second data block, and the second data block receives uc, calculates the total fitting value ue2 using the formula ue2=ua2+uc, and calculates the total loss loss2 based on the total fitting value ue2 and the true value using the loss function;

The second data block calculates the gradient factor gdf based on the total fitting value ue2 and the true value, and encrypts the gradient factor gdf to obtain the encrypted gdf;

The second data block sends the encrypted gdf to the third data party, and the third data party calculates the encrypted gradient gdhc based on the encrypted gdf;

Based on the homomorphic encryption algorithm, the third data party generates a random number Rc and encrypts Rc to obtain an encrypted Rb. The third data party sends the sum of the encrypted gradient gdhc and the encrypted Rc to the second data block;

The second data block decrypts the sum of the encrypted gradient gdhc and the encrypted Rc into gdhd=gdhc+Rc, and sends gdhd to the third data party;

The third data party receives and updates the weight wc according to gdhd minus the random number Rc;

The second data block obtains the gradient gdha2 by multiplying the feature and gdf matrix, and updates the weight wa2 and bias intercept2 according to the gradient gdha2.

Exemplarily, please refer to Figure 4, which shows a flow chart of the interaction between a second data block and a third data party provided by an embodiment of the present invention. The data interaction process between A2 and C is consistent with the data interaction process between A1 and B. The process of vertical federation between A2 and C is as follows: A2 sends the homomorphic encryption public key to C. A2 and C each fit the initial values of the parameters, where A2 initializes the weight wa2 and the bias intercept2; C initializes the weight wc. A2 and C each calculate the dot product of the features and parameters. A2 transmits the dot product result uc of the features and parameters to A2, and A2 calculates the total fitting value ue2 of A2 and C. The total loss is calculated using the loss function based on the total fitting value and the true value: Party A2 calculates the gradient factor based on the total fitting value and the true value at the same time: gdf = xwT-y = y`-y. Party A2 sends the encrypted [gdf] to Party C, and Party C calculates the encrypted gradient of Party C [gdhc] based on the encrypted [gdf]. Gradient = (feature column) matrix multiplication (gradient factor). Party C generates a random number and encrypts it [Rc]. Party B then sends the encrypted gradient and the encrypted random number [gdhc] + [Rc] to Party A2. Party A2 decrypts the encrypted gradient and the encrypted random number to gdhd = gdhc + Rc, and Party A2 sends gdhd to Party C. Party A2 obtains Party A2's gradient gdha2 by multiplying the feature and gdf matrix. Party A2 updates Party A2's weights wa2 and intercept2 based on gdha2. Party C updates Party C's weight wc based on gdhd minus the added random number Rc, thus completing a round of vertical federated parameter update.

Please refer to Figure 6, which is a schematic structural block diagram of an electronic device provided in an embodiment of the present application. The electronic device includes a memory 101, a processor 102 and a communication interface 103, and the memory 101, the processor 102 and the communication interface 103 are electrically connected to each other directly or indirectly to realize data transmission or interaction. For example, these components can be electrically connected to each other through one or more communication buses or signal lines. The memory 101 can be used to store software programs and modules, and the processor 102 executes various functional applications and data processing by executing the software programs and modules stored in the memory 101. The communication interface 103 can be used to communicate signaling or data with other node devices.

Among them, the memory 101 can be but is not limited to, random access memory (Random Access Memory, RAM), read-only memory (Read Only Memory, ROM), programmable read-only memory (Programmable Read-Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM), electrically erasable read-only memory (Electric Erasable Programmable Read-Only Memory, EEPROM), etc.

The processor 102 may be an integrated circuit chip having signal processing capability. The processor 102 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NPU), a It can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

It is understood that the structure shown in Figure 6 is only for illustration, and the electronic device may also include more or fewer components than those shown in Figure 6, or have a different configuration than that shown in Figure 6. Each component shown in Figure 6 may be implemented by hardware, software, or a combination thereof.

In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to the multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and/or the flowchart, and the combination of boxes in the block diagram and/or the flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

It will be apparent to those skilled in the art that the present application is not limited to the details of the exemplary embodiments described above, and that the present application can be implemented in other specific forms without departing from the spirit or essential features of the present application. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims be included in the present application. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims (7)

A hybrid federated logistic regression method based on homomorphic encryption, characterized by comprising the following steps: Perform module segmentation on the data of the first data cube to obtain a first data block and a second data block, and form data data1 from the first data block and the second data cube, and form data data2 from the second data block and the third data cube; Perform longitudinal federated logistic regression training on the data data1, merge parameters to obtain w1, intercept1 and loss1, perform longitudinal federated logistic regression training on the data data2, merge parameters to obtain w2, intercept2 and loss2; According to the merge parameters, perform horizontal federated logistic regression calculations on data1 and data2 respectively; For data data1 or data data2, each participant calls the key exchange protocol to obtain the same random number r, and uses the random number r as a seed to generate a homomorphic public and private key pair; According to the aggregation interval parameter, encrypt w1 and intercept1, and encrypt w2 and intercept2 at the same time to obtain encryption parameters, and send the encryption parameters to the collaborating party for secure aggregation to obtain aggregation intermediate result parameters; The collaborating party sends the aggregated intermediate result parameters to each participating party, and each participating party decrypts the aggregated intermediate result parameters and performs the next round of parameter iteration according to the decrypted aggregated intermediate result parameters until the requirements are met to obtain the final training model. The hybrid federated logistic regression method based on homomorphic encryption according to claim 1 is characterized in that the step of performing longitudinal federated logistic regression training on the data data1 comprises: Based on the homomorphic encryption algorithm, the first data block generates a homomorphic encryption public key, and sends the homomorphic encryption public key to the second data party, and the second data party receives the homomorphic encryption public key; The first data block and the second data block each fit the initial values of the parameters, wherein the first data block initializes the weight wa1 and the bias intercept1, and the second data block initializes the weight wb; The first data block calculates the dot product of the feature and the parameter to obtain ua1, and the second data block calculates the dot product of the feature and the parameter to obtain ub; The second data block transmits ub to the first data block, and the first data block receives ub, calculates the total fitting value ue1 using the formula ue1=ua1+ub, and calculates the total loss loss1 based on the total fitting value ue1 and the true value using the loss function: The first data block calculates a gradient factor gdf based on the total fitting value ue1 and the true value, and encrypts the gradient factor gdf to obtain an encrypted gdf; The first data block sends the encrypted gdf to the second data party, and the second data party calculates the corresponding encryption gradient gdhb according to the encrypted gdf; Based on the homomorphic encryption algorithm, the second data party generates a random number Rb and encrypts Rb to obtain encrypted Rb, and the second data party sends the sum of the encrypted gradient gdhb and the encrypted Rb to the first data block; The first data block decrypts the sum into gdhd=gdhb+Rb, and sends gdhd to the second data party; The second data party receives gdhd, calculates a gradient gdhb according to a formula gdhb=gdhd-Rb, and updates a weight wb according to the gradient gdhb; The first data block obtains the gradient gdha1 by multiplying the feature and the gdf matrix, and updates the weight wa1 and the bias intercept1 according to the gradient gdha1. The hybrid federated logistic regression method based on homomorphic encryption according to claim 2 is characterized in that the step of calculating the gradient factor gdf based on the total fitting value ue1 and the true value of the first data block comprises: The gradient factor gdf is calculated using the formula gdf=xwT-y, where xwT represents the fitting value and y represents the true value. The hybrid federated logistic regression method based on homomorphic encryption according to claim 2 is characterized in that the step of the second data cube calculating the corresponding encrypted gradient gdhb according to the encrypted gdf comprises: The encrypted gradient gdhb is calculated according to the formula encrypted gradient gdhb=gradient factor gdf*Xb, where Xb represents the feature column matrix. The hybrid federated logistic regression method based on homomorphic encryption according to claim 1 is characterized in that the step of performing longitudinal federated logistic regression training on the data data2 comprises: Based on the homomorphic encryption algorithm, the second data block sends the homomorphic encryption public key to the third data party, and the third data party receives the homomorphic encryption public key; The second data block and the third data block each fit the initial values of the parameters, wherein the second data block initializes the weight wa2 and the bias intercept2, and the third data block initializes the weight wc; The second data block calculates the dot product of the feature and the parameter to obtain ua2, and the third data block calculates the dot product of the feature and the parameter to obtain uc; The third data party transmits uc to the second data block, the second data block receives uc, calculates the total fitting value ue2 using the formula ue2=ua2+uc, and calculates the total loss loss2 based on the total fitting value ue2 and the true value using the loss function; The second data block calculates the gradient factor gdf based on the total fitting value ue2 and the true value, and encrypts the gradient factor gdf to obtain the encrypted gdf; The second data block sends the encrypted gdf to the third data party, and the third data party calculates the encrypted gradient gdhc according to the encrypted gdf; Based on the homomorphic encryption algorithm, the third data party generates a random number Rc and encrypts Rc to obtain an encrypted Rb, and the third data party sends the sum of the encrypted gradient gdhc and the encrypted Rc to the second data block; The second data block decrypts the sum of the encrypted gradient gdhc and the encrypted Rc into gdhd=gdhc-Rc, and sends gdhd to the third data party; The third data party receives and updates the weight wc according to gdhd minus the random number Rc; The second data block obtains the gradient gdha2 by multiplying the feature and the gdf matrix, and updates the weight wa2 and the bias intercept2 according to the gradient gdha2. An electronic device, comprising: A memory for storing one or more programs; processor; When the one or more programs are executed by the processor, the method according to any one of claims 1 to 5 is implemented. A computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.