CN115879650A - Multi-task joint prediction method and system based on credible block chain multi-state separation - Google Patents
Multi-task joint prediction method and system based on credible block chain multi-state separation Download PDFInfo
- Publication number
- CN115879650A CN115879650A CN202310138818.9A CN202310138818A CN115879650A CN 115879650 A CN115879650 A CN 115879650A CN 202310138818 A CN202310138818 A CN 202310138818A CN 115879650 A CN115879650 A CN 115879650A
- Authority
- CN
- China
- Prior art keywords
- prediction
- data
- decrypted
- request
- encrypted
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000000926 separation method Methods 0.000 title claims abstract description 21
- 238000004891 communication Methods 0.000 claims abstract description 10
- 230000011218 segmentation Effects 0.000 claims abstract description 9
- 239000010410 layer Substances 0.000 claims description 23
- 239000012792 core layer Substances 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 description 9
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Images
Abstract
The invention discloses a credible multi-task joint prediction method and a credible system based on block chain polymorphic separation, wherein the method comprises the steps of initializing a block chain of each participant; generating a key and a corresponding communication address for each party; according to the prediction data and the prediction request of each participant at the same moment, encrypting by using a corresponding key, and determining the encrypted prediction data and the encrypted prediction request; decrypting the encrypted prediction data and the encrypted prediction requests of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data; segmenting the prediction result according to the decrypted prediction request; synchronizing the segmented prediction results, and then correspondingly distributing the prediction results to the participants; and simultaneously destroying and logging the decrypted request data. The method can ensure reliable sharing of data and effective segmentation of results in multi-joint combined prediction in the current traffic scene.
Description
Technical Field
The invention relates to the field of block chains, in particular to a credible multi-task joint prediction method and system based on block chain polymorphic separation.
Background
Under the condition of traffic big data, various prediction scenes are usually complexly fused by multiple unknown factors, a certain kind of data owned by a single party in the conventional situation only reflects a certain direction characteristic in a certain scene, and all effective characteristics of the scene cannot be accurately described at all, so that a single-data and single-task prediction algorithm cannot be used for comprehensively, objectively and accurately predicting the certain scene. Therefore, the demand of a multi-task joint prediction algorithm in a traffic scene is greatly increased, the algorithm usually needs to use multi-party data, the data of each party is the characteristic description of a certain dimension of the problem, and the algorithm realizes the comprehensive description of the problem through deep learning and other modes on the basis of fusing the data of each party.
The core of the multi-task joint prediction algorithm is to fuse the characteristic description data of each party. In the present case, data is the value and results are the value. The core problems are two: 1. how data is shared; data usually involves some privacy and is inconvenient to share, and how to ensure reliable sharing of the data is a problem to be solved; 2. how the outcomes are divided; and the data of all parties are used for jointly predicting the formed result, so that the segmentation can be effectively carried out without causing the correction.
Therefore, in order to solve the problems that data cannot be reliably shared and results cannot be effectively segmented in multi-joint prediction in the current traffic scene, a new task joint prediction method or system needs to be provided urgently.
Disclosure of Invention
The invention aims to provide a credible multi-task joint prediction method and system based on block chain polymorphic separation, which can ensure reliable data sharing and effective achievement segmentation in multi-joint prediction under the current traffic scene.
In order to achieve the purpose, the invention provides the following scheme:
a credible multi-task joint prediction method based on block chain polymorphic separation comprises the following steps:
initializing a blockchain of each participant;
generating a key and a corresponding communication address for each party;
according to the prediction data and the prediction request of each participant at the same moment, encrypting by using a corresponding key, and determining the encrypted prediction data and the encrypted prediction request;
decrypting the encrypted prediction data and the encrypted prediction requests of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data;
segmenting the prediction result according to the decrypted prediction request; synchronizing the segmented prediction results, and then correspondingly distributing the prediction results to the participants; and simultaneously destroying and logging the decrypted request data.
Optionally, the determining, according to the prediction data and the prediction request of each participant at the same time, the encrypted prediction data and the encrypted prediction request by using the corresponding key, further includes:
carrying out data preprocessing on the decrypted prediction data and the decrypted prediction request; the data preprocessing comprises the following steps: and (4) data completion, data matrixing and normalization processing.
Optionally, the joint prediction algorithm comprises: convolutional neural networks, cyclic neural networks, and long-short term memory networks.
A credible multi-task joint prediction system based on block chain polymorphic separation is applied to the credible multi-task joint prediction method based on block chain polymorphic separation, and the system comprises the following steps:
the initialization unit is used for initializing the block chain of each participant;
a parameter generating unit for generating a key and a corresponding communication address of each participant;
the encryption unit is used for encrypting according to the prediction data and the prediction request of each participant at the same moment by using a corresponding key and determining the encrypted prediction data and the encrypted prediction request;
a prediction result determining unit for decrypting the encrypted prediction data and the encrypted prediction request of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data;
the prediction result segmentation and distribution unit is used for segmenting the prediction result according to the decrypted prediction request; synchronizing the segmented prediction results, and then correspondingly distributing the prediction results to the participants; and simultaneously destroying the decrypted request data.
A credible multi-task joint prediction system based on block chain polymorphic separation is applied to the credible multi-task joint prediction method based on block chain polymorphic separation, and the system comprises the following steps: the system comprises a front-end management layer, a core layer, an IO layer and a multi-link access layer;
the front-end management layer is used for managing a joint prediction algorithm, displaying the state of each participant and carrying out configuration operation;
the core layer is used for decrypting the encrypted prediction data and the encrypted prediction requests of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data; segmenting the prediction result according to the decrypted prediction request; simultaneously destroying and logging the decrypted request data; the core layer is also used for synchronizing the decrypted prediction data and the decrypted prediction request and synchronizing the segmented prediction result;
the IO layer is used for accessing and outputting prediction data and prediction requests of each participant, and simultaneously performing identity authentication and authority management, data caching and data preprocessing;
the multi-link access layer is used to initialize the blockchain for each participant.
Optionally, the core layer comprises: a joint prediction algorithm module and a chain synchronization module;
the joint prediction algorithm module is used for decrypting the encrypted prediction data and the encrypted prediction requests of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data; segmenting the prediction result according to the decrypted prediction request; simultaneously destroying and logging the decrypted request data;
and the chain synchronization module is used for synchronizing the decrypted prediction data and the decrypted prediction request and synchronizing the segmented prediction result.
Optionally, the IO layer includes: the system comprises an authority management module and an IO module;
the authority management module is used for generating a secret key of each participant, sending the secret key to the participants and simultaneously performing management, identity authentication and authority management on the secret key;
the IO module is used for configuring a communication address corresponding to each participant.
Optionally, the encryption method includes: RSA and DES.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the block chain of each participant is initialized, each participant can only access the block chain of the participant, information provided by each participant is integrally predicted through a joint prediction algorithm, a prediction result is segmented according to requirements, the segmented result is returned to each participant according to the requirements, each participant forms respective requests and result chains, and the secure data sharing and result segmentation of each participant are effectively realized. The information of other participants can not be known by any party, and meanwhile, after the algorithm runs the round of task, data of all parties can be destroyed, so that the data can not be leaked.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flow chart of a reliable multi-task joint prediction method based on block chain polymorphic separation according to the present invention;
FIG. 2 is a schematic diagram of a work flow of an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a reliable multitask joint prediction system based on block chain polymorphic separation according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a credible multi-task joint prediction method and system based on block chain polymorphic separation, which can ensure reliable data sharing and effective achievement segmentation in multi-joint prediction under the current traffic scene.
In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, the present invention is described in detail with reference to the accompanying drawings and the detailed description thereof.
As shown in fig. 1, the method for multi-task joint prediction based on credible block chain polymorphic separation provided by the present invention includes:
s101, initializing a block chain of each participant;
s102, generating a key and a corresponding communication address of each participant;
s103, encrypting by using a corresponding key according to the prediction data and the prediction request of each participant at the same moment, and determining the encrypted prediction data and the encrypted prediction request;
before S103, further comprising:
carrying out data preprocessing on the decrypted prediction data and the decrypted prediction request; the data preprocessing comprises the following steps: and (4) data completion, data matrixing and normalization processing.
The data preprocessing process comprises the following steps:
wherein: f () is a data processing algorithm, such as data completion, etc., and a, B, C are the own partial prediction data of the current round provided by the corresponding parties a, B, C. A common data completion algorithm is an averaging method, that is, a missing data value is an average value of the whole input data, and the formula is as follows:
wherein the content of the first and second substances,
the input data mean value is, n is the data quantity, and a is the input data of the current participant A.
And forming a complete processing matrix M by the prediction data of all the participating input legal persons formed in the first step, wherein each row of the matrix is normalized data. Any normalization algorithm, such as zero-mean normalization (Z-score normalization), can be used for each input datum, and the formula is as follows:
wherein the content of the first and second substances,
is the mean of the raw data, is greater than or equal to>
Is the standard deviation of the original data. />
For each element value in the matrix, <' > H>
Is a normalized value. If the values of the inputs are very different, the method can be used to normalize the inputs and then combine them into a matrix.
N participators form N input matrixes, the dimensionalities of the matrixes can be the same or different, the matrix is implemented according to a specific joint prediction algorithm, and finally a final input data matrix is formed
，
Is an input matrix for participants a, B, c.
S104, decrypting the encrypted prediction data and the encrypted prediction requests of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data; the joint prediction algorithm comprises: convolutional neural networks, cyclic neural networks, and long-short term memory networks.
As a specific example, as shown in FIG. 2, the prediction result is
(ii) a Wherein F denotes the joint prediction algorithm and O denotes the output of the algorithm, is>
For each partyAnd (5) a result after segmentation.
Wherein, the typical joint prediction algorithm is multi-path CNN, and the main steps include convolution, pooling, output and the like; wherein, convolution: here, the input matrix size is w, the convolution kernel size is k, the stride is s, and the number of zero padding layers is p, then the size calculation formula of the feature map generated after convolution is:
for the output, a matrix stretching mode can be adopted, and the convolution output of the previous step is stretched and segmented:
can be directly cut into the parts of the Chinese medicinal materials,
；/>
after the participators A, B, C and N receive the result, namely A receives the above R a B receives R b And then, checking the result, generating a result block of the request according to the requirement, and carrying out uplink on the result block.
S105, segmenting a prediction result according to the decrypted prediction request; synchronizing the segmented prediction results, and then correspondingly distributing the prediction results to the participants; and simultaneously destroying and logging the decrypted request data.
As a specific embodiment, corresponding to the method, the present invention provides a reliable multitask joint prediction system based on block chain polymorphic separation, and the system includes:
the initialization unit is used for initializing the block chain of each participant;
a parameter generating unit for generating a key and a corresponding communication address for each party;
the encryption unit is used for encrypting according to the prediction data and the prediction request of each participant at the same moment by using a corresponding key and determining the encrypted prediction data and the encrypted prediction request;
a prediction result determining unit for decrypting the encrypted prediction data and the encrypted prediction request of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data;
the prediction result segmentation and distribution unit is used for segmenting the prediction result according to the decrypted prediction request; synchronizing the segmented prediction results, and then correspondingly distributing the prediction results to the participants; and simultaneously destroying the decrypted request data.
As shown in fig. 3, the present invention further provides a credible multitask joint prediction system based on block chain polymorphic separation, and the system includes: a front end management layer, a core layer, an IO layer and a multi-link access layer;
the front-end management layer is used for managing a joint prediction algorithm, displaying the state of each participant and carrying out configuration operation;
the core layer is used for decrypting the encrypted prediction data and the encrypted prediction requests of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data; segmenting the prediction result according to the decrypted prediction request; meanwhile, the decrypted request data is destroyed and logged; the core layer is also used for synchronizing the decrypted prediction data and the decrypted prediction request and synchronizing the segmented prediction result;
the IO layer is used for accessing and outputting prediction data and prediction requests of each participant, and simultaneously performing identity authentication and authority management, data caching and data preprocessing;
the multi-link access layer is used to initialize the blockchain for each participant.
The core layer includes: a joint prediction algorithm module and a chain synchronization module;
the joint prediction algorithm module is used for decrypting the encrypted prediction data and the encrypted prediction requests of all the participants at the same moment; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data; segmenting the prediction result according to the decrypted prediction request; simultaneously destroying and logging the decrypted request data;
and the chain synchronization module is used for synchronizing the decrypted prediction data and the decrypted prediction request and synchronizing the segmented prediction result.
The IO layer includes: the system comprises an authority management module and an IO module;
the authority management module is used for generating a secret key of each participant, sending the secret key to the participants and simultaneously performing management, identity authentication and authority management on the secret key;
the IO module is used for configuring a communication address corresponding to each participant.
The IO layer mainly processes data access, output and authority management, where data access and output refer to collecting data of each participant in an encrypted form and sending the encrypted data to each participant, including but not limited to caching and preprocessing of data. The data collection and transmission forms include but are not limited to streaming data and non-streaming data, and the data access and transmission forms include but are not limited to message queues, http requests and the like.
The encryption mode comprises the following steps: RSA and DES.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. A credible multitask joint prediction method based on block chain polymorphic separation is characterized by comprising the following steps:
initializing a block chain of each participant;
generating a key and a corresponding communication address for each participant;
according to the prediction data and the prediction request of each participant at the same moment, encrypting by using a corresponding key, and determining the encrypted prediction data and the encrypted prediction request;
decrypting the encrypted prediction data and the encrypted prediction requests of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data;
segmenting the prediction result according to the decrypted prediction request; synchronizing the segmented prediction results, and then correspondingly distributing the prediction results to the participants; and simultaneously destroying and logging the decrypted request data.
2. The method according to claim 1, wherein the encrypted prediction data and the encrypted prediction request are determined according to the prediction data and the prediction request of each participant at the same time and by encrypting the prediction data and the prediction request with a corresponding key, and the method further comprises:
carrying out data preprocessing on the decrypted prediction data and the decrypted prediction request; the data preprocessing comprises the following steps: and (4) data completion, data matrixing and normalization processing.
3. The method according to claim 1, wherein the joint prediction algorithm comprises: convolutional neural networks, cyclic neural networks, and long-short term memory networks.
4. A credible multitask joint prediction system based on block chain polymorphic separation, which is applied to the credible multitask joint prediction method based on block chain polymorphic separation according to any one of claims 1 to 3, and is characterized in that the system comprises:
the initialization unit is used for initializing the block chain of each participant;
a parameter generating unit for generating a key and a corresponding communication address for each party;
the encryption unit is used for encrypting according to the prediction data and the prediction request of each participant at the same moment by using a corresponding key and determining the encrypted prediction data and the encrypted prediction request;
a prediction result determining unit for decrypting the encrypted prediction data and the encrypted prediction request of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data;
the prediction result segmentation and distribution unit is used for segmenting the prediction result according to the decrypted prediction request; synchronizing the segmented prediction results, and then correspondingly distributing the prediction results to the participants; and simultaneously destroying the decrypted request data.
5. A credible multitask joint prediction system based on block chain polymorphic separation, which is applied to the credible multitask joint prediction method based on block chain polymorphic separation according to any one of claims 1 to 3, and is characterized in that the system comprises: a front end management layer, a core layer, an IO layer and a multi-link access layer;
the front-end management layer is used for managing a joint prediction algorithm, displaying the state of each participant and carrying out configuration operation;
the core layer is used for decrypting the encrypted prediction data and the encrypted prediction requests of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data; segmenting the prediction result according to the decrypted prediction request; simultaneously destroying and logging the decrypted request data; the core layer is also used for synchronizing the decrypted prediction data and the decrypted prediction request and synchronizing the segmented prediction result;
the IO layer is used for accessing and outputting prediction data and prediction requests of each participant, and simultaneously performing identity authentication and authority management, data caching and data preprocessing;
the multi-link access layer is used to initialize the blockchain for each participant.
6. The system according to claim 5, wherein the core layer comprises: a joint prediction algorithm module and a chain synchronization module;
the joint prediction algorithm module is used for decrypting the encrypted prediction data and the encrypted prediction requests of all the participants at the same time; determining a prediction result by adopting a joint prediction algorithm according to the decrypted prediction data; segmenting the prediction result according to the decrypted prediction request; simultaneously destroying and logging the decrypted request data;
and the chain synchronization module is used for synchronizing the decrypted prediction data and the decrypted prediction request and synchronizing the segmented prediction result.
7. The system according to claim 5, wherein the IO layer comprises: the system comprises an authority management module and an IO module;
the authority management module is used for generating a key of each participant, sending the key to the participants, and simultaneously performing key management, identity authentication and authority management;
the IO module is used for configuring a communication address corresponding to each participant.
8. The system according to claim 7, wherein the encryption scheme comprises: RSA and DES.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310138818.9A CN115879650A (en) | 2023-02-21 | 2023-02-21 | Multi-task joint prediction method and system based on credible block chain multi-state separation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310138818.9A CN115879650A (en) | 2023-02-21 | 2023-02-21 | Multi-task joint prediction method and system based on credible block chain multi-state separation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115879650A true CN115879650A (en) | 2023-03-31 |
Family
ID=85761368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310138818.9A Pending CN115879650A (en) | 2023-02-21 | 2023-02-21 | Multi-task joint prediction method and system based on credible block chain multi-state separation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115879650A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113553609A (en) * | 2021-09-17 | 2021-10-26 | 支付宝(杭州)信息技术有限公司 | Method and system for predicting service by combining multiple parties based on privacy protection |
| CN113722753A (en) * | 2021-08-25 | 2021-11-30 | 银清科技有限公司 | Privacy data processing method, device and system based on block chain |
| CN114580689A (en) * | 2020-11-30 | 2022-06-03 | 深圳前海微众银行股份有限公司 | Service prediction method, device, equipment, storage medium and program product |
| CN114610994A (en) * | 2022-03-09 | 2022-06-10 | 支付宝(杭州)信息技术有限公司 | Push method and system based on joint prediction |
| CN115357664A (en) * | 2022-10-21 | 2022-11-18 | 北京航空航天大学 | Multidirectional trusted system based on block chain and data query method |
-
2023
- 2023-02-21 CN CN202310138818.9A patent/CN115879650A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114580689A (en) * | 2020-11-30 | 2022-06-03 | 深圳前海微众银行股份有限公司 | Service prediction method, device, equipment, storage medium and program product |
| CN113722753A (en) * | 2021-08-25 | 2021-11-30 | 银清科技有限公司 | Privacy data processing method, device and system based on block chain |
| CN113553609A (en) * | 2021-09-17 | 2021-10-26 | 支付宝(杭州)信息技术有限公司 | Method and system for predicting service by combining multiple parties based on privacy protection |
| CN114610994A (en) * | 2022-03-09 | 2022-06-10 | 支付宝(杭州)信息技术有限公司 | Push method and system based on joint prediction |
| CN115357664A (en) * | 2022-10-21 | 2022-11-18 | 北京航空航天大学 | Multidirectional trusted system based on block chain and data query method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110268691B (en) | Federated blockchain networks with verified blockchain and consensus protocols | |
| CN111556120B (en) | Data processing method and device based on block chain, storage medium and equipment | |
| US11082482B2 (en) | Block chain encoding with fair delay for distributed network devices | |
| CN107172056A (en) | A kind of channel safety determines method, device, system, client and server | |
| US20230254129A1 (en) | Key management for multi-party computation | |
| US11470065B2 (en) | Protection of private data using an enclave cluster | |
| US10749670B2 (en) | Block chain decoding with fair delay for distributed network devices | |
| CN114254386A (en) | Federated learning privacy protection system and method based on hierarchical aggregation and block chain | |
| CN114417364A (en) | Data encryption method, federal modeling method, apparatus and computer device | |
| US20190384905A1 (en) | Image based authentication code method, server, and authentication code system | |
| Cheng et al. | SecureAD: A secure video anomaly detection framework on convolutional neural network in edge computing environment | |
| GB2594741A (en) | Multi-directional zero-knowledge attestation systems and methods | |
| KR102389690B1 (en) | Content delivery system | |
| US20220038270A1 (en) | Data processing system and method | |
| CN113840115A (en) | Monitoring video data encryption transmission system and method based on block chain | |
| CN117395077A (en) | Encryption processing method and device for access request, computer equipment and storage medium | |
| CN115134080B (en) | Data transmission method and device based on security encryption chip | |
| CN115879650A (en) | Multi-task joint prediction method and system based on credible block chain multi-state separation | |
| CN114710370B (en) | Fine-grained access control method and system based on fog block chain and attribute encryption | |
| CN115758402A (en) | Artificial intelligence model federal learning method combining homomorphic encryption and model watermarking | |
| CN115114667A (en) | Privacy information processing and classifying method and device for security chip | |
| CN114650188A (en) | Data secure transmission method and device based on proxy node | |
| CN111368309B (en) | Information processing method, system and equipment | |
| Agarwala et al. | Client side secure image deduplication using DICE protocol | |
| CN117171766B (en) | Data protection method, system and medium based on deep neural network model |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230331 |
|
| RJ01 | Rejection of invention patent application after publication |