CN113810168A - Training method of machine learning model, server and computer equipment - Google Patents

Training method of machine learning model, server and computer equipment Download PDF

Info

Publication number
CN113810168A
CN113810168A CN202011607378.XA CN202011607378A CN113810168A CN 113810168 A CN113810168 A CN 113810168A CN 202011607378 A CN202011607378 A CN 202011607378A CN 113810168 A CN113810168 A CN 113810168A
Authority
CN
China
Prior art keywords
machine learning
learning model
ciphertext
data
key
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011607378.XA
Other languages
Chinese (zh)
Inventor
代子营
王铁成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jingdong Technology Holding Co Ltd
Original Assignee
Jingdong Technology Holding Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jingdong Technology Holding Co Ltd filed Critical Jingdong Technology Holding Co Ltd
Priority to CN202011607378.XA priority Critical patent/CN113810168A/en
Publication of CN113810168A publication Critical patent/CN113810168A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/008—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols involving homomorphic encryption
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00—Network architectures or network communication protocols for network security
    • H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
    • H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload

Abstract

The application provides a training method of a machine learning model, a server and computer equipment, wherein the method comprises the following steps: generating a homomorphic key pair, wherein the homomorphic key pair comprises a public key and a private key; sending the public key to a plurality of data owner servers so that the data owner servers encrypt the data of the data owner servers through the public key and send ciphertext data generated after encryption to a machine learning server, wherein the machine learning server performs model training and testing according to the ciphertext data provided by the data owner servers so as to generate a ciphertext machine learning model; and receiving the ciphertext machine learning model sent by the machine learning server, and decrypting the ciphertext machine learning model according to the private key to form a plaintext machine learning model, so that data provided by the data owner server can be protected, the plaintext machine learning model can be protected, and the safety is high.

Description

Training method of machine learning model, server and computer equipment
Technical Field
The present application relates to the field of information processing technologies, and in particular, to a training method for a machine learning model, a server, and a computer device.
Background
In the related art, in a scene of machine learning model training based on multi-source data, a data owner server provides plaintext data to a machine learning server, and the machine learning server trains an initial machine learning model according to the plaintext data to form a plaintext machine learning model.
In the above method, it is difficult to protect the security of the plaintext data provided by the data owner server, and it is difficult to protect the plaintext machine learning model, which is poor in security.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art.
The application provides a training method of a machine learning model, a server and computer equipment, so that data provided by a data owner server are encrypted, and an initial machine learning model is trained by encrypted ciphertext data, so that the data provided by the data owner server can be protected, a plaintext machine learning model can be protected, and the safety is high.
An embodiment of a first aspect of the present application provides a training method for a machine learning model, including:
generating a homomorphic key pair, wherein the homomorphic key pair comprises a public key and a private key;
sending the public key to a plurality of data owner servers so that the data owner servers encrypt the data of the data owner servers through the public key and send ciphertext data generated after encryption to a machine learning server, wherein the machine learning server performs model training and testing according to the ciphertext data provided by the data owner servers so as to generate a ciphertext machine learning model; and
and receiving the ciphertext machine learning model sent by the machine learning server, and decrypting the ciphertext machine learning model according to the private key to form a plaintext machine learning model.
According to the training method of the machine learning model, a homomorphic key pair is generated, wherein the homomorphic key pair comprises a public key and a private key; sending the public key to a plurality of data owner servers so that the data owner servers encrypt the data of the data owner servers through the public key and send ciphertext data generated after encryption to a machine learning server, wherein the machine learning server performs model training and testing according to the ciphertext data provided by the data owner servers so as to generate a ciphertext machine learning model; and receiving the ciphertext machine learning model sent by the machine learning server, and decrypting the ciphertext machine learning model according to the private key to form a plaintext machine learning model, so that data provided by the data owner server can be protected, the plaintext machine learning model can be protected, and the safety is high.
The embodiment of the second aspect of the present application provides a training method of a machine learning model, including:
receiving ciphertext data sent by a plurality of data owner servers, wherein the ciphertext data are generated after the data of the data owner servers are encrypted through a public key in a homomorphic key pair;
training and testing a machine learning model according to the ciphertext data to generate a ciphertext machine learning model;
and sending the ciphertext machine learning model to a key management server so that the key management server decrypts by using a private key in the homomorphic key pair to form a plaintext machine learning model.
According to the training method of the machine learning model, ciphertext data sent by a plurality of data owner servers are received, wherein the ciphertext data are generated after the data of the data owner servers are encrypted through public keys in homomorphic key pairs; training and testing the machine learning model according to the ciphertext data to generate a ciphertext machine learning model; and sending the ciphertext machine learning model to the key management server so that the key management server decrypts the private key in the homomorphic key pair by adopting the private key to form a plaintext machine learning model, thereby protecting the data provided by the data owner server, protecting the plaintext machine learning model and ensuring high safety.
The embodiment of the third aspect of the application provides a training method of a machine learning model, which comprises the following steps:
receiving a public key sent by a key management server, wherein the public key is a public key in a homomorphic key pair;
encrypting self data by adopting the public key to generate ciphertext data;
and sending the ciphertext data to a machine learning server, wherein the machine learning server performs model training and testing according to the received ciphertext data to generate a ciphertext machine learning model, and sends the ciphertext machine learning model to the key management server for decryption to form a plaintext machine learning model.
In the training method of the machine learning model in the embodiment of the application, the public key sent by the key management server is received, and the public key is a public key in a homomorphic key pair; encrypting the data by adopting a public key to generate ciphertext data; and sending the ciphertext data to a machine learning server, wherein the machine learning server performs model training and testing according to the received ciphertext data to generate a ciphertext machine learning model, and sends the ciphertext machine learning model to a key management server for decryption to form a plaintext machine learning model, so that data provided by a data owner server can be protected, the plaintext machine learning model can be protected, and the safety is high.
An embodiment of a fourth aspect of the present application provides a key management server, including:
the generating module is used for generating a homomorphic key pair, wherein the homomorphic key pair comprises a public key and a private key;
the sending module is used for sending the public key to a plurality of data owner servers so that the data owner servers encrypt the data of the data owner servers through the public key and send ciphertext data generated after encryption to the machine learning server, wherein the machine learning server conducts model training and testing according to the ciphertext data provided by the data owner servers so as to generate a ciphertext machine learning model;
and the decryption module is used for receiving the ciphertext machine learning model sent by the machine learning server and decrypting the ciphertext machine learning model according to the private key to form a plaintext machine learning model.
The key management server generates a homomorphic key pair, wherein the homomorphic key pair comprises a public key and a private key; sending the public key to a plurality of data owner servers so that the data owner servers encrypt the data of the data owner servers through the public key and send ciphertext data generated after encryption to a machine learning server, wherein the machine learning server performs model training and testing according to the ciphertext data provided by the data owner servers so as to generate a ciphertext machine learning model; and receiving the ciphertext machine learning model sent by the machine learning server, and decrypting the ciphertext machine learning model according to the private key to form a plaintext machine learning model, so that data provided by the data owner server can be protected, the plaintext machine learning model can be protected, and the safety is high.
An embodiment of a fifth aspect of the present application provides a machine learning server, including:
the system comprises a receiving module, a sending module and a receiving module, wherein the receiving module is used for receiving ciphertext data sent by a plurality of data owner servers, and the ciphertext data is generated after the data of the data owner servers are encrypted by a public key in a homomorphic key pair;
the training module is used for training and testing a machine learning model according to the ciphertext data to generate a ciphertext machine learning model;
and the sending module is used for sending the ciphertext machine learning model to a key management server so that the key management server decrypts by adopting a private key in the homomorphic key pair to form a plaintext machine learning model.
The machine learning server receives ciphertext data sent by a plurality of data owner servers, wherein the ciphertext data is generated by the plurality of data owner servers after encrypting the data of the data owner servers through a public key in a homomorphic key pair; training and testing the machine learning model according to the ciphertext data to generate a ciphertext machine learning model; and sending the ciphertext machine learning model to the key management server so that the key management server decrypts the private key in the homomorphic key pair by adopting the private key to form a plaintext machine learning model, thereby protecting the data provided by the data owner server, protecting the plaintext machine learning model and ensuring high safety.
An embodiment of a sixth aspect of the present application provides a data owner server, including:
the receiving module is used for receiving a public key sent by a key management server, wherein the public key is a public key in a homomorphic key pair;
the encryption module is used for encrypting the data by adopting the public key to generate ciphertext data;
and the sending module is used for sending the ciphertext data to a machine learning server, wherein the machine learning server performs model training and testing according to the received ciphertext data to generate a ciphertext machine learning model, and sends the ciphertext machine learning model to the key management server for decryption to form a plaintext machine learning model.
The data owner server receives the public key sent by the key management server, wherein the public key is a public key in a homomorphic key pair; encrypting the data by adopting a public key to generate ciphertext data; and sending the ciphertext data to a machine learning server, wherein the machine learning server performs model training and testing according to the received ciphertext data to generate a ciphertext machine learning model, and sends the ciphertext machine learning model to a key management server for decryption to form a plaintext machine learning model, so that data provided by a data owner server can be protected, the plaintext machine learning model can be protected, and the safety is high.
An embodiment of a seventh aspect of the present application provides a computer device, including: the computer program may be stored in a memory and executed on a processor, where the processor implements a method for training a machine learning model as set forth in embodiments of the first aspect, the second aspect, or the third aspect of the present application.
An eighth aspect of the present application provides a computer program product, and when executed by an instruction processor in the computer program product, the method for training a machine learning model provided in the first, second, or third aspect of the present application is performed.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of a training method of a machine learning model according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of a training method of a machine learning model according to a second embodiment of the present application;
fig. 3 is a schematic flowchart of a training method of a machine learning model according to a third embodiment of the present application;
fig. 4 is a schematic structural diagram of a key management server according to a fourth embodiment of the present application;
fig. 5 is a schematic structural diagram of a machine learning server according to a fifth embodiment of the present application;
fig. 6 is a schematic structural diagram of a data owner server according to a sixth embodiment of the present application;
FIG. 7 illustrates a block diagram of an exemplary computer device suitable for use to implement embodiments of the present application.
Detailed Description
Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
In the traditional training method of the machine learning model, the data owner server provides plaintext data for the machine learning server, and the machine learning server trains the initial machine learning model according to the plaintext data to form the plaintext machine learning model.
However, in the above method, it is difficult to protect the security of the plaintext data provided by the data owner server, and it is difficult to protect the plaintext machine learning model, and the security is poor.
The application scenario of the method is that the machine learning task is executed in a large organization. Executing a machine learning task, namely learning a machine learning model; the learning of machine learning models requires the use of data from various departments dispersed within the organization. It is impractical to integrate data of each department and then learn a machine learning model for reasons of competition between the departments, security, and administrative management of each department. In the case of meeting the regulatory requirements, it is necessary to select a higher-level manager, for example, a higher-level department of each department, and to ensure the security of data of each department and the security of the machine learning model by using the key management service managed by the higher-level manager.
Therefore, the present application provides a training method for a machine learning model, mainly aiming at the technical problems in the prior art that the security of plaintext data provided by a data owner server is poor and the security of a plaintext machine learning model is poor.
According to the training method of the machine learning model, a homomorphic key pair is generated, wherein the homomorphic key pair comprises a public key and a private key; sending the public key to a plurality of data owner servers so that the data owner servers encrypt the data of the data owner servers through the public key and send ciphertext data generated after encryption to a machine learning server, wherein the machine learning server performs model training and testing according to the ciphertext data provided by the data owner servers so as to generate a ciphertext machine learning model; and receiving the ciphertext machine learning model sent by the machine learning server, and decrypting the ciphertext machine learning model according to the private key to form a plaintext machine learning model, so that data provided by the data owner server can be protected, the plaintext machine learning model can be protected, and the safety is high.
The following describes a training method, a server, and a computer device of a machine learning model according to an embodiment of the present application with reference to the drawings.
Fig. 1 is a flowchart illustrating a training method of a machine learning model according to an embodiment of the present disclosure.
The embodiment of the present application is exemplified by the method for training a machine learning model being configured in a training apparatus of a machine learning model, and the training apparatus of a machine learning model can be applied to any computer device, so that the computer device can perform a training function of the machine learning model. The computer device may be, for example, a key management server. In the embodiment of the present application, a computer device is taken as an example of a key management server for description.
The Computer device may be a Personal Computer (PC), a cloud device, a mobile device, and the like, and the mobile device may be a hardware device having various operating systems, touch screens, and/or display screens, such as a mobile phone, a tablet Computer, a Personal digital assistant, a wearable device, and an in-vehicle device.
As shown in fig. 1, the training method of the machine learning model may include the following steps:
step 101, generating a homomorphic key pair, wherein the homomorphic key pair comprises a public key and a private key.
In the embodiment of the application, homomorphic encryption means that data which is subjected to homomorphic encryption is processed to obtain an output, and the output is decrypted, wherein the result is the same as the output result obtained by processing unencrypted original data by the same method. The homomorphic encryption comprises 4 algorithms and two keys, wherein the 4 algorithms are respectively a key generation algorithm (Keygen), an encryption algorithm (Enc), a decryption algorithm (Dec) and an evaluation algorithm (Eval); the two keys are respectively a public key (pk) and a private key (sk). The key generation algorithm is used for generating a key; the encryption algorithm is used for encrypting the data by combining the public key to generate ciphertext data; the decryption algorithm is used for decrypting the ciphertext data by combining the private key; and the evaluation algorithm is used for carrying out evaluation processing on the ciphertext data by combining the public key, the ciphertext data and the calculation function, and the data obtained after the decryption of the evaluation processing result is consistent with the data obtained after the plaintext data is processed by adopting the calculation function.
In the embodiment of the present application, the way for the key management server to generate the homomorphic key pair may specifically be a homomorphic key pair generated according to a homomorphic encrypted key generation algorithm. And generating a homomorphic key pair by using a homomorphic encryption key generation algorithm based on preset parameters. The preset parameters (setup) are, for example, security parameters, multiplication depth, etc., and are selected according to the particular homomorphic encryption algorithm used. The method is suitable for all homomorphic encryption algorithms (homomorphic encryption) meeting the requirements of machine learning model training and prediction calculation.
And 102, sending the public key to a plurality of data owner servers so that the data owner servers encrypt the data of the data owner servers through the public key and send ciphertext data generated after encryption to a machine learning server, wherein the machine learning server performs model training and testing according to the ciphertext data provided by the data owner servers to generate a ciphertext machine learning model.
In the embodiment of the present application, in order to further improve security, the key management server may send the public key to the plurality of data owner servers through the secure channel.
In the embodiment of the application, the key management server can also send the public key to the machine learning server through a secure channel. Correspondingly, the machine learning server performs model training and testing according to ciphertext data provided by the data owner servers to generate a ciphertext machine learning model, and performs evaluation processing on the ciphertext data, the training and testing algorithm of the machine learning model and the public key by adopting a homomorphic encryption evaluation algorithm to obtain the ciphertext machine learning model.
In the embodiment of the application, the training of the machine learning model and the evaluation process of the test algorithm are implemented according to the homomorphic encryption algorithm. The process is suitable for all homomorphic encryption algorithms (homomorphic encryption) meeting the requirements of machine learning model training and test calculation.
And 103, receiving the ciphertext machine learning model sent by the machine learning server, and decrypting the ciphertext machine learning model according to the private key to form a plaintext machine learning model.
In this embodiment, the process of the key management server executing step 103 may be, for example, decrypting the ciphertext machine learning model by using a decryption algorithm and a private key that are homomorphic encrypted, so as to generate a plaintext machine learning model. The private key and the ciphertext machine learning model are input in a homomorphic encryption decryption algorithm, the private key and the ciphertext machine learning model are input in the homomorphic encryption decryption algorithm, and a result obtained through calculation is the plaintext machine learning model.
According to the training method of the machine learning model, a homomorphic key pair is generated, wherein the homomorphic key pair comprises a public key and a private key; sending the public key to a plurality of data owner servers so that the data owner servers encrypt the data of the data owner servers through the public key and send ciphertext data generated after encryption to a machine learning server, wherein the machine learning server performs model training and testing according to the ciphertext data provided by the data owner servers so as to generate a ciphertext machine learning model; and receiving the ciphertext machine learning model sent by the machine learning server, and decrypting the ciphertext machine learning model according to the private key to obtain the plaintext machine learning model, so that the data provided by the data owner server can be protected, the plaintext machine learning model can be protected, and the safety is high.
Fig. 2 is a flowchart illustrating a training method of a machine learning model according to a second embodiment of the present application.
The embodiment of the present application is exemplified by the method for training a machine learning model being configured in a training apparatus of a machine learning model, and the training apparatus of a machine learning model can be applied to any computer device, so that the computer device can perform a training function of the machine learning model. The computer device may be, for example, a machine learning server. In the embodiment of the present application, a computer device is taken as an example of a machine learning server for description.
The Computer device may be a Personal Computer (PC), a cloud device, a mobile device, and the like, and the mobile device may be a hardware device having various operating systems, touch screens, and/or display screens, such as a mobile phone, a tablet Computer, a Personal digital assistant, a wearable device, and an in-vehicle device.
As shown in fig. 2, the training method of the machine learning model may include the following steps:
step 201, receiving ciphertext data sent by a plurality of data owner servers, where the ciphertext data is generated by the plurality of data owner servers encrypting their own data with a public key in a homomorphic key pair.
In the embodiment of the application, the machine learning server can receive ciphertext data sent by a plurality of data owner servers through a secure channel. The public keys used by the plurality of data owner servers are sent to the data owner server by the key management server through a secure channel.
In the embodiment of the present application, the way for the data owner server to obtain the ciphertext data may be, for example, to encrypt the data of the data owner server by using a homomorphic encryption algorithm and a public key to obtain the ciphertext data. The public key and the self data are input into the homomorphic encryption algorithm, and the result obtained through calculation is ciphertext data.
And step 202, training and testing the machine learning model according to the ciphertext data to generate the ciphertext machine learning model.
In this embodiment of the present application, the process of the machine learning server executing step 202 may specifically be to receive a public key sent by the key management server; and evaluating the ciphertext data, the training and testing algorithm of the machine learning model and the public key by adopting a homomorphic encryption evaluation algorithm to obtain the ciphertext machine learning model.
In the embodiment of the application, the training of the machine learning model and the evaluation process of the test algorithm are implemented according to the homomorphic encryption algorithm. The process is suitable for all homomorphic encryption algorithms (homomorphic encryption) meeting the requirements of machine learning model training and test calculation.
Step 203, sending the ciphertext machine learning model to the key management server, so that the key management server decrypts the private key in the homomorphic key pair to form a plaintext machine learning model.
In the embodiment of the present application, the process of the key management server decrypting with the private key in the homomorphic key pair to form the plaintext machine learning model may be, for example, decrypting the ciphertext machine learning model with the decryption algorithm and the private key encrypted in the homomorphic manner to generate the plaintext machine learning model. The private key and the ciphertext machine learning model are input in a homomorphic encryption decryption algorithm, the private key and the ciphertext machine learning model are input in the homomorphic encryption decryption algorithm, and a result obtained through calculation is the plaintext machine learning model.
According to the training method of the machine learning model, ciphertext data sent by a plurality of data owner servers are received, wherein the ciphertext data are generated after the data of the data owner servers are encrypted through public keys in homomorphic key pairs; training and testing the machine learning model according to the ciphertext data to generate a ciphertext machine learning model; and sending the ciphertext machine learning model to the key management server so that the key management server decrypts the private key in the homomorphic key pair by adopting the private key to form a plaintext machine learning model, thereby protecting the data provided by the data owner server, protecting the plaintext machine learning model and ensuring high safety.
Fig. 3 is a flowchart illustrating a training method of a machine learning model according to a third embodiment of the present application.
The embodiment of the present application is exemplified by the method for training a machine learning model being configured in a training apparatus of a machine learning model, and the training apparatus of a machine learning model can be applied to any computer device, so that the computer device can perform a training function of the machine learning model. The computer device may be, for example, a data owner server. In the embodiment of the present application, a computer device is taken as an example of a data owner server for description.
The Computer device may be a Personal Computer (PC), a cloud device, a mobile device, and the like, and the mobile device may be a hardware device having various operating systems, touch screens, and/or display screens, such as a mobile phone, a tablet Computer, a Personal digital assistant, a wearable device, and an in-vehicle device.
As shown in fig. 3, the training method of the machine learning model may include the following steps:
step 301, a public key sent by the key management server is received, and the public key is a public key in a homomorphic key pair.
In the embodiment of the present application, in order to further improve security, the data owner server may receive, through a secure channel, the public key sent by the key management server. The mode of generating the homomorphic key pair by the key management server may specifically be a homomorphic key pair generated according to a homomorphic encrypted key generation algorithm. And generating a homomorphic key pair by using a homomorphic encryption key generation algorithm based on preset parameters. The preset parameters, such as security parameters, multiplication depth, etc., are selected according to the particular homomorphic encryption algorithm used. The method is suitable for all homomorphic encryption algorithms (homomorphic encryption) meeting the requirements of machine learning model training and prediction calculation.
And step 302, encrypting the self data by adopting the public key to generate ciphertext data.
In this embodiment of the application, the process of the data owner server executing step 302 may specifically be that an encryption algorithm and a public key that are homomorphic for encryption are used to encrypt the data of the data owner server, so as to obtain ciphertext data. The public key and the self data are input into the homomorphic encryption algorithm, and the result obtained through calculation is ciphertext data.
And step 303, sending the ciphertext data to a machine learning server, wherein the machine learning server performs model training and testing according to the received ciphertext data to generate a ciphertext machine learning model, and sends the ciphertext machine learning model to a key management server for decryption to form a plaintext machine learning model.
In the embodiment of the application, the process of the machine learning server performing model training and testing according to the received ciphertext data to generate the ciphertext machine learning model may be, for example, receiving a public key sent by a key management server; and evaluating the ciphertext data, the training and testing algorithm of the machine learning model and the public key by adopting a homomorphic encryption evaluation algorithm to obtain the ciphertext machine learning model.
In the embodiment of the present application, the process of the key management server decrypting with the private key in the homomorphic key pair to form the plaintext machine learning model may be, for example, decrypting the ciphertext machine learning model with the decryption algorithm and the private key encrypted in the homomorphic manner to generate the plaintext machine learning model. The private key and the ciphertext machine learning model are input in a homomorphic encryption decryption algorithm, the private key and the ciphertext machine learning model are input in the homomorphic encryption decryption algorithm, and a result obtained through calculation is the plaintext machine learning model.
In the training method of the machine learning model in the embodiment of the application, the public key sent by the key management server is received, and the public key is a public key in a homomorphic key pair; encrypting the data by adopting a public key to generate ciphertext data; and sending the ciphertext data to a machine learning server, wherein the machine learning server performs model training and testing according to the received ciphertext data to generate a ciphertext machine learning model, and sends the ciphertext machine learning model to a key management server for decryption to form a plaintext machine learning model, so that data provided by a data owner server can be protected, the plaintext machine learning model can be protected, and the safety is high.
Fig. 4 is a schematic structural diagram of a key management server according to a fourth embodiment of the present application.
As shown in fig. 4, the key management server 400 may include: a generating module 410, a transmitting module 420 and a decrypting module 430.
The generating module 410 is configured to generate a homomorphic key pair, where the homomorphic key pair includes a public key and a private key;
a sending module 420, configured to send the public key to multiple data owner servers, so that the multiple data owner servers encrypt their own data through the public key, and send ciphertext data generated after encryption to a machine learning server, where the machine learning server performs model training and testing on the ciphertext data provided by the multiple data owner servers to generate a ciphertext machine learning model;
and the decryption module 430 is configured to receive the ciphertext machine learning model sent by the machine learning server, and decrypt the ciphertext machine learning model according to the private key to form a plaintext machine learning model.
Further, in a possible implementation manner of the embodiment of the present application, the generating module 410 is specifically configured to generate the homomorphic key pair according to a homomorphic encryption key generation algorithm.
Further, in a possible implementation manner of the embodiment of the present application, the sending module 420 is specifically configured to send the public key to the plurality of data owner servers through a secure channel.
Further, in a possible implementation manner of the embodiment of the present application, the sending module 420 is further configured to send the public key to the machine learning server. The machine learning server performs model training and testing according to ciphertext data provided by the data owner servers to generate a ciphertext machine learning model, and evaluates the ciphertext data, the training and testing algorithm of the machine learning model and the public key by using a homomorphic encryption evaluation algorithm to obtain the ciphertext machine learning model.
Further, in a possible implementation manner of the embodiment of the present application, the decryption module 430 is specifically configured to decrypt the ciphertext machine learning model by using a decryption algorithm of homomorphic encryption and the private key, so as to generate the plaintext machine learning model.
It should be noted that the explanation in the first embodiment is also applicable to the key management server in this embodiment, and details are not described here.
The key management server generates a homomorphic key pair, wherein the homomorphic key pair comprises a public key and a private key; sending the public key to a plurality of data owner servers so that the data owner servers encrypt the data of the data owner servers through the public key and send ciphertext data generated after encryption to a machine learning server, wherein the machine learning server performs model training and testing according to the ciphertext data provided by the data owner servers so as to generate a ciphertext machine learning model; and receiving the ciphertext machine learning model sent by the machine learning server, and decrypting the ciphertext machine learning model according to the private key to form a plaintext machine learning model, so that data provided by the data owner server can be protected, the plaintext machine learning model can be protected, and the safety is high.
Fig. 5 is a schematic structural diagram of a machine learning server according to a fifth embodiment of the present application.
As shown in fig. 5, the machine learning server 500 may include: a receive module 510, a training module 520, and a transmit module 530.
The receiving module 510 is configured to receive ciphertext data sent by multiple data owner servers, where the ciphertext data is data generated by the multiple data owner servers after encrypting their own data with a public key in a homomorphic key pair;
the training module 520 is configured to perform training and testing on a machine learning model according to the ciphertext data to generate a ciphertext machine learning model;
a sending module 530, configured to send the ciphertext machine learning model to a key management server, so that the key management server decrypts by using a private key in the homomorphic key pair to form a plaintext machine learning model.
Further, in a possible implementation manner of the embodiment of the present application, the training module 520 is specifically configured to receive the public key sent by the key management server; and evaluating the ciphertext data, the training and testing algorithm of the machine learning model and the public key by adopting a homomorphic encryption evaluation algorithm to obtain the ciphertext machine learning model.
Further, in a possible implementation manner of the embodiment of the application, the receiving module 510 is specifically configured to receive the public key sent by the key management server through a secure channel.
It should be noted that the explanation in the second embodiment is also applicable to the machine learning server in this embodiment, and is not described herein again.
The machine learning server receives ciphertext data sent by a plurality of data owner servers, wherein the ciphertext data is generated by the plurality of data owner servers after encrypting the data of the data owner servers through a public key in a homomorphic key pair; training and testing the machine learning model according to the ciphertext data to generate a ciphertext machine learning model; and sending the ciphertext machine learning model to the key management server so that the key management server decrypts the private key in the homomorphic key pair by adopting the private key to form a plaintext machine learning model, thereby protecting the data provided by the data owner server, protecting the plaintext machine learning model and ensuring high safety.
Fig. 6 is a schematic structural diagram of a data owner server according to a sixth embodiment of the present application.
As shown in fig. 6, the data owner server 600 may include: a receiving module 610, an encryption module 620, and a transmitting module 630.
The receiving module 610 is configured to receive a public key sent by a key management server, where the public key is a public key in a homomorphic key pair;
the encryption module 620 is configured to encrypt data of the user by using the public key to generate ciphertext data;
the sending module 630 is configured to send the ciphertext data to a machine learning server, where the machine learning server performs model training and testing according to the received ciphertext data to generate a ciphertext machine learning model, and sends the ciphertext machine learning model to the key management server to decrypt to form a plaintext machine learning model.
Further, in a possible implementation manner of the embodiment of the present application, the encryption module 620 is specifically configured to obtain an encryption algorithm of homomorphic encryption; and encrypting the self data by adopting the homomorphic encryption algorithm and the public key to generate ciphertext data.
Further, in a possible implementation manner of the embodiment of the present application, the receiving module 610 is specifically configured to receive the public key sent by the key management server through a secure channel.
It should be noted that the explanation in the third embodiment is also applicable to the data owner server in this embodiment, and details are not described here.
The data owner server receives the public key sent by the key management server, wherein the public key is a public key in a homomorphic key pair; encrypting the data by adopting a public key to generate ciphertext data; and sending the ciphertext data to a machine learning server, wherein the machine learning server performs model training and testing according to the received ciphertext data to generate a ciphertext machine learning model, and sends the ciphertext machine learning model to a key management server for decryption to form a plaintext machine learning model, so that data provided by a data owner server can be protected, the plaintext machine learning model can be protected, and the safety is high.
In order to implement the foregoing embodiments, the present application also provides a computer device, including: the computer program can be stored in a memory of the computer system, and can be executed on the processor.
In order to implement the foregoing embodiments, the present application also provides a computer program product, which when executed by an instruction processor in the computer program product, performs the training method of the machine learning model as set forth in the foregoing embodiments of the present application.
FIG. 7 illustrates a block diagram of an exemplary computer device suitable for use to implement embodiments of the present application. The computer device 12 shown in fig. 7 is only an example, and should not bring any limitation to the function and the scope of use of the embodiments of the present application.
As shown in FIG. 7, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. These architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus, to name a few.
Computer device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
Memory 28 may include computer system readable media in the form of volatile Memory, such as Random Access Memory (RAM) 30 and/or cache Memory 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 7, and commonly referred to as a "hard drive"). Although not shown in FIG. 7, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described herein.
Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with computer device 12, and/or with any devices (e.g., network card, modem, etc.) that enable computer device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Moreover, computer device 12 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network such as the Internet) via Network adapter 20. As shown, network adapter 20 communicates with the other modules of computer device 12 via bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes various functional applications and data processing, for example, implementing the methods mentioned in the foregoing embodiments, by executing programs stored in the system memory 28.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims (24)

1. A method for training a machine learning model, comprising:
generating a homomorphic key pair, wherein the homomorphic key pair comprises a public key and a private key;
sending the public key to a plurality of data owner servers so that the data owner servers encrypt the data of the data owner servers through the public key and send ciphertext data generated after encryption to a machine learning server, wherein the machine learning server performs model training and testing according to the ciphertext data provided by the data owner servers so as to generate a ciphertext machine learning model; and
and receiving the ciphertext machine learning model sent by the machine learning server, and decrypting the ciphertext machine learning model according to the private key to form a plaintext machine learning model.
2. The method of training of a machine learning model of claim 1, wherein the generating a homomorphic key pair comprises:
and generating the homomorphic key pair according to a homomorphic encryption key generation algorithm.
3. A method of training a machine learning model as defined in claim 1, wherein the public key is sent to the plurality of data owner servers over a secure channel.
4. The method of training a machine learning model of claim 1, further comprising:
sending the public key to the machine learning server;
wherein the machine learning server performs model training and testing according to the ciphertext data provided by the plurality of data owner servers to generate a ciphertext machine learning model,
and evaluating the ciphertext data, the training and testing algorithm of the machine learning model and the public key by adopting a homomorphic encryption evaluation algorithm to obtain the ciphertext machine learning model.
5. A method of training a machine learning model as claimed in claim 1 wherein said decrypting from said private key to form a plaintext machine learning model comprises:
and decrypting the ciphertext machine learning model by adopting a homomorphic encryption decryption algorithm and the private key to generate the plaintext machine learning model.
6. A method for training a machine learning model, comprising:
receiving ciphertext data sent by a plurality of data owner servers, wherein the ciphertext data are generated after the data of the data owner servers are encrypted through a public key in a homomorphic key pair;
training and testing a machine learning model according to the ciphertext data to generate a ciphertext machine learning model;
and sending the ciphertext machine learning model to a key management server so that the key management server decrypts by using a private key in the homomorphic key pair to form a plaintext machine learning model.
7. The method for training a machine learning model according to claim 6, wherein the training and testing of the machine learning model according to the ciphertext data to generate the ciphertext machine learning model comprises:
receiving the public key sent by the key management server;
and evaluating the ciphertext data, the training and testing algorithm of the machine learning model and the public key by adopting a homomorphic encryption evaluation algorithm to obtain the ciphertext machine learning model.
8. A method for training a machine learning model according to claim 7, wherein said receiving the public key sent by the key management server comprises:
and receiving the public key sent by the key management server through a secure channel.
9. A method for training a machine learning model, comprising:
receiving a public key sent by a key management server, wherein the public key is a public key in a homomorphic key pair;
encrypting self data by adopting the public key to generate ciphertext data;
and sending the ciphertext data to a machine learning server, wherein the machine learning server performs model training and testing according to the received ciphertext data to generate a ciphertext machine learning model, and sends the ciphertext machine learning model to the key management server for decryption to form a plaintext machine learning model.
10. The training method of machine learning model according to claim 9, wherein the encrypting the self data by using the public key to generate ciphertext data includes:
obtaining an encryption algorithm of homomorphic encryption;
and encrypting the self data by adopting the homomorphic encryption algorithm and the public key to generate ciphertext data.
11. The method for training a machine learning model according to claim 9, wherein the receiving the public key transmitted by the key management server comprises:
and receiving the public key sent by the key management server through a secure channel.
12. A key management server, comprising:
the generating module is used for generating a homomorphic key pair, wherein the homomorphic key pair comprises a public key and a private key;
the sending module is used for sending the public key to a plurality of data owner servers so that the data owner servers encrypt the data of the data owner servers through the public key and send ciphertext data generated after encryption to the machine learning server, wherein the machine learning server conducts model training and testing according to the ciphertext data provided by the data owner servers so as to generate a ciphertext machine learning model;
and the decryption module is used for receiving the ciphertext machine learning model sent by the machine learning server and decrypting the ciphertext machine learning model according to the private key to form a plaintext machine learning model.
13. The key management server according to claim 12,
the generating module is specifically configured to generate the homomorphic key pair according to a homomorphic encryption key generation algorithm.
14. The key management server according to claim 12,
the sending module is specifically configured to send the public key to the plurality of data owner servers through a secure channel.
15. The key management server of claim 12, wherein the sending module is further to send the public key to the machine learning server;
wherein the machine learning server performs model training and testing according to the ciphertext data provided by the plurality of data owner servers to generate a ciphertext machine learning model,
and evaluating the ciphertext data, the training and testing algorithm of the machine learning model and the public key by adopting a homomorphic encryption evaluation algorithm to obtain the ciphertext machine learning model.
16. The key management server of claim 12, wherein the decryption module is specifically configured to,
and decrypting the ciphertext machine learning model by adopting a homomorphic encryption decryption algorithm and the private key to generate the plaintext machine learning model.
17. A machine learning server, comprising:
the system comprises a receiving module, a sending module and a receiving module, wherein the receiving module is used for receiving ciphertext data sent by a plurality of data owner servers, and the ciphertext data is generated after the data of the data owner servers are encrypted by a public key in a homomorphic key pair;
the training module is used for training and testing a machine learning model according to the ciphertext data to generate a ciphertext machine learning model;
and the sending module is used for sending the ciphertext machine learning model to a key management server so that the key management server decrypts by adopting a private key in the homomorphic key pair to form a plaintext machine learning model.
18. The machine learning server of claim 17, wherein the training module is specific to,
receiving the public key sent by the key management server;
and evaluating the ciphertext data, the training and testing algorithm of the machine learning model and the public key by adopting a homomorphic encryption evaluation algorithm to obtain the ciphertext machine learning model.
19. The machine learning server of claim 17, wherein the receiving module is specifically to,
and receiving the public key sent by the key management server through a secure channel.
20. A data owner server, comprising:
the receiving module is used for receiving a public key sent by a key management server, wherein the public key is a public key in a homomorphic key pair;
the encryption module is used for encrypting the data by adopting the public key to generate ciphertext data;
and the sending module is used for sending the ciphertext data to a machine learning server, wherein the machine learning server performs model training and testing according to the received ciphertext data to generate a ciphertext machine learning model, and sends the ciphertext machine learning model to the key management server for decryption to form a plaintext machine learning model.
21. The data owner server according to claim 20, wherein the encryption module is specifically configured to,
obtaining an encryption algorithm of homomorphic encryption;
and encrypting the self data by adopting the homomorphic encryption algorithm and the public key to generate ciphertext data.
22. The data owner server according to claim 20, wherein the receiving module is specifically configured to,
and receiving the public key sent by the key management server through a secure channel.
23. An electronic device, comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-11.
24. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-11.
CN202011607378.XA 2020-12-30 2020-12-30 Training method of machine learning model, server and computer equipment Pending CN113810168A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011607378.XA CN113810168A (en) 2020-12-30 2020-12-30 Training method of machine learning model, server and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011607378.XA CN113810168A (en) 2020-12-30 2020-12-30 Training method of machine learning model, server and computer equipment

Publications (1)

Publication Number Publication Date
CN113810168A true CN113810168A (en) 2021-12-17

Family

ID=78943595

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011607378.XA Pending CN113810168A (en) 2020-12-30 2020-12-30 Training method of machine learning model, server and computer equipment

Country Status (1)

Country Link
CN (1) CN113810168A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115001566A (en) * 2022-07-07 2022-09-02 浙江天翼通智能科技有限公司 Unmanned aerial vehicle cluster cooperative processing method
CN115037442A (en) * 2022-08-11 2022-09-09 平安银行股份有限公司 Model effect detection method and device, storage medium and equipment
CN115664632A (en) * 2022-11-10 2023-01-31 苏州浪潮智能科技有限公司 Prediction model training method, system, equipment and medium based on homomorphic encryption

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110572253A (en) * 2019-09-16 2019-12-13 济南大学 Method and system for enhancing privacy of federated learning training data
CN110719158A (en) * 2019-09-11 2020-01-21 南京航空航天大学 Edge calculation privacy protection system and method based on joint learning
US20200125739A1 (en) * 2018-10-19 2020-04-23 International Business Machines Corporation Distributed learning preserving model security
CN111260081A (en) * 2020-02-14 2020-06-09 广州大学 Non-interactive privacy protection multi-party machine learning method

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200125739A1 (en) * 2018-10-19 2020-04-23 International Business Machines Corporation Distributed learning preserving model security
CN110719158A (en) * 2019-09-11 2020-01-21 南京航空航天大学 Edge calculation privacy protection system and method based on joint learning
CN110572253A (en) * 2019-09-16 2019-12-13 济南大学 Method and system for enhancing privacy of federated learning training data
CN111260081A (en) * 2020-02-14 2020-06-09 广州大学 Non-interactive privacy protection multi-party machine learning method

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
林鹏飞: "同态加密在隐私保护下分布式机器学习中的应用研究", 《万方数据知识服务平台》 *
许心炜等: "基于同态加密的多分类Logistic 回归模型", 《密码学报》, no. 2, pages 179 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115001566A (en) * 2022-07-07 2022-09-02 浙江天翼通智能科技有限公司 Unmanned aerial vehicle cluster cooperative processing method
CN115037442A (en) * 2022-08-11 2022-09-09 平安银行股份有限公司 Model effect detection method and device, storage medium and equipment
CN115037442B (en) * 2022-08-11 2022-11-29 平安银行股份有限公司 Model effect detection method and device, storage medium and equipment
CN115664632A (en) * 2022-11-10 2023-01-31 苏州浪潮智能科技有限公司 Prediction model training method, system, equipment and medium based on homomorphic encryption

Similar Documents

Publication Publication Date Title
CN109255247B (en) Multi-party security calculation method and device and electronic equipment
CN113505894B (en) Longitudinal federal learning linear regression and logistic regression model training method and device
CN113810168A (en) Training method of machine learning model, server and computer equipment
US10027640B2 (en) Secure data re-encryption
WO2022105627A1 (en) Secure re-encryption of homomorphically encrypted data
CN105468940B (en) Method for protecting software and device
US11381381B2 (en) Privacy preserving oracle
US20170310479A1 (en) Key Replacement Direction Control System and Key Replacement Direction Control Method
JP2010517448A (en) Secure file encryption
CN112491529B (en) Data file encryption and integrity verification method and system used in untrusted server environment
KR20180110550A (en) Method and apparatus for white-box cryptography for protecting against side channel analysis
US9755832B2 (en) Password-authenticated public key encryption and decryption
US9571273B2 (en) Method and system for the accelerated decryption of cryptographically protected user data units
CN112149174A (en) Model training method, device, equipment and medium
US10223249B2 (en) Test methodology for detection of unwanted cryptographic key destruction
CN102473219B (en) Communication channel claim dependent security precautions
JP2021530009A (en) Secure behavior for encrypted data
CN112149140B (en) Prediction method, prediction device, prediction equipment and storage medium
US8929555B2 (en) Data encryption systems and methods
CN115225367A (en) Data processing method, device, computer equipment, storage medium and product
CN110474967B (en) Block chain experiment system and method
JP5799876B2 (en) Program, information processing method and information processing apparatus
CN109756506A (en) Data ciphering method, device, equipment and storage medium based on GNSS receiver
CN110995749A (en) Block chain encryption method and device, electronic equipment and storage medium
CN111464282B (en) Homomorphic encryption-based data processing method and device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination