CN113328864A - Data transmission method and system based on function encryption, block chain and machine learning - Google Patents

Abstract

The present disclosure provides a data transmission method and system based on functional encryption, blockchain and machine learning. An edge server performs functional encryption on edge data to obtain edge encrypted data, and sends it to a cloud storage server; the structure of the edge server corresponds to the edge encrypted data. The data transaction information is sent to the blockchain server; the edge server sends the constructed and trained token generation model to the central server, and the central server uses the token generation model to generate tokens; among them, the token generation model is machine learning Model; the central server obtains and verifies the data transaction information from the blockchain server, and in response to determining that the data transaction information has passed the verification, uses the token to decrypt the edge encrypted data obtained from the cloud storage server, and obtains a preset range of data in the edge data. By combining the related operations of data encryption with the transactions in the blockchain, the reliability of edge data is guaranteed by the inability to tamper with the blockchain.

Description

Data transmission method and system based on functional encryption, blockchain and machine learning

technical field

The present disclosure relates to the technical field of data transmission, and in particular, to a data transmission method and system based on functional encryption, block chain and machine learning.

Background technique

In the "central server-edge server" data management system, when the central server needs to obtain the edge data in the edge server, the edge server will use the private key to encrypt the edge data to obtain the ciphertext information of the edge data, and send the ciphertext information to the The central server uses the public key to decrypt the ciphertext information to obtain the plaintext information of the edge data for reference and use.

However, in the existing data transmission methods, potential malicious edge servers may damage the reliability of edge data, such as destroying other edge servers, eavesdropping on keys, uploading forged data information, etc., the reliability of edge data cannot be guaranteed. .

SUMMARY OF THE INVENTION

In view of this, the purpose of the present disclosure is to propose a data transmission method and system based on functional encryption, blockchain and machine learning.

Based on the above purpose, the present disclosure provides a data transmission method based on functional encryption, blockchain and machine learning. The method is implemented by an edge server, a central server, a blockchain server and a cloud storage server. The method includes:

The edge server performs functional encryption on the edge data to obtain edge encrypted data, and sends the edge encrypted data to the cloud storage server;

The edge server constructs data transaction information corresponding to the edge encrypted data, and sends the data transaction information to the blockchain server;

The edge server sends the constructed and trained token generation model to the central server, and the central server uses the token generation model to generate tokens; wherein the token generation model is a machine learning model;

The central server obtains and verifies the data transaction information from the blockchain server, and in response to determining that the data transaction information passes the verification, decrypts the edge encrypted data obtained from the cloud storage server by using the token , to obtain data of a preset range in the edge data.

Based on the same inventive concept, the present disclosure provides a data transmission system based on functional encryption, blockchain and machine learning, including an edge server, a central server, a blockchain server and a cloud storage server, the system is used to realize the above method described.

It can be seen from the above that the data transmission method and system based on functional encryption, blockchain and machine learning provided by the present disclosure include: the edge server performs functional encryption on the edge data to obtain the edge encrypted data, and sends the edge encrypted data. to the cloud storage server; the edge server constructs the data transaction information corresponding to the edge encrypted data, and sends the data transaction information to the blockchain server; the edge server sends the constructed and trained token generation model to the central server, and the central server uses The token generation model generates tokens; wherein, the token generation model is a machine learning model; the central server obtains and verifies the data transaction information from the blockchain server, and in response to determining that the data transaction information passes the verification, uses the token to decrypt the data from the cloud storage server The acquired edge encrypted data obtains data of a preset range in the edge data. By combining the related operations of data encryption with the transactions in the blockchain, the reliability of edge data is guaranteed by the inability to tamper with the blockchain.

Description of drawings

In order to illustrate the technical solutions in the present disclosure or related technologies more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only for the present disclosure. In the embodiments, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without any creative effort.

1 is a schematic diagram of a structure of a center-edge data management system in the related art;

2 is a schematic flowchart of a data transmission method based on functional encryption, block chain and machine learning provided by an embodiment of the present disclosure;

3 is a schematic diagram of an algorithm for generating data transaction information provided by an embodiment of the present disclosure;

4 is a schematic diagram of a data transaction information verification algorithm provided by an embodiment of the present disclosure;

FIG. 5 is a schematic structural diagram of a data transmission system based on functional encryption, block chain and machine learning provided by an embodiment of the present disclosure;

FIG. 6 is a more specific schematic diagram of the architecture of the data transmission system based on functional encryption, block chain and machine learning provided by an embodiment of the present disclosure;

7 is a schematic diagram of a result of a first simulation experiment provided by an embodiment of the present disclosure;

FIG. 8 is a schematic diagram of the results of a second simulation experiment provided by an embodiment of the present disclosure;

FIG. 9 is a more specific schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present disclosure clearer, the present disclosure will be further described in detail below with reference to the specific embodiments and the accompanying drawings.

It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should have the usual meanings understood by those with ordinary skill in the art to which the present disclosure belongs. "First", "second" and similar words used in the embodiments of the present disclosure do not denote any order, quantity or importance, but are only used to distinguish different components. "Comprises" or "comprising" and similar words mean that the elements or things appearing before the word encompass the elements or things recited after the word and their equivalents, but do not exclude other elements or things. Words like "connected" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "Down", "Left", "Right", etc. are only used to represent the relative positional relationship, and when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

Referring to FIG. 1, it is a schematic diagram of an architecture of a center-edge data management system in the related art; in a center-edge (center server-edge server) data management system, first, the edge server is registered with the center server, and the center server pairs The edge server performs authentication and authorization, thereby establishing a mutual trust relationship between the central server and the edge server, including reaching an agreement and sending keys. When the central server applies to obtain the edge data in the edge server, the edge server will use the private key to encrypt the edge data to obtain the ciphertext information of the edge data, and send the ciphertext information to the central server, and the central server will use the public key to decrypt the ciphertext information. , so as to obtain the plaintext information of the edge data to consult and use the edge data.

However, in the above data transmission method, a potentially malicious edge server may damage the reliability of edge data, such as violating the signed agreement, destroying other edge servers, eavesdropping on keys, and uploading forged data information, etc. However, The central server cannot effectively identify potentially malicious edge servers, so the reliability of edge data cannot be guaranteed.

In view of this, the present disclosure proposes a data transmission method and system based on functional encryption, blockchain and machine learning.

Referring to FIG. 2 , which is a schematic flowchart of a data transmission method based on functional encryption, block chain and machine learning provided by an embodiment of the present disclosure. The method is implemented by an edge server, a central server, a blockchain server and a cloud storage server. Among them, there is only one central server, and there can be multiple edge servers. There is no limit to the number of blockchain servers and cloud storage servers.

When implementing the data transmission method based on functional encryption, blockchain, and machine learning provided by the embodiments of the present disclosure for the first time, it is first necessary to construct a key between the central server and the edge server (that is, private key), and the edge server and the central server need to be registered in the blockchain server, and the blockchain server generates the public key and private key for the edge server (for the convenience of distinction, This disclosure refers to edge server public key and edge server private key).

Specifically, the method further includes: the central server generates a master public key and a master private key, and sends the master public key to the edge server.

In some embodiments, the central server includes an authorization server and a service server.

The authorization server obtains the security parameter λ. The security parameter here is a parameter that is input when some required initial values are generated in the cryptographic encryption algorithm, and it is a requirement that the key and other data in the algorithm are computationally unbreakable. In general, the larger the security parameter, the higher the security of the cryptographic algorithm. In practice, a relatively large security constant (such as 128) is generally selected directly. Generate an asymmetric bilinear paired group system PG=(p,G ₁ ,G ₂ ,G _T ,e,g ₁ ,g ₂ ), where p is a prime number, which is automatically generated according to the security parameters; G ₁ ,G ₂ , G _T are both p-order groups; g ₁ , g ₂ are generators of groups G ₁ and G ₂ respectively; e is a bilinear map, and e = G ₁ ×G ₂ → G _T .

The authorization server randomly selects two vectors s, t∈Z _p ⁿ , and calculates g ₁ ^s and g ₂ ^t ; specifically, for any s∈{1,2,T}, g _s represents the generation of different groups element, if it is an integer x∈Z _p , it is represented by [x] _s = g _s ^x ∈ G _s , and if it is a vector x∈Z _p ⁿ , it is also represented by [x] _s = g _s ^x ∈ G _s ; From this, the master public key and the master private key are calculated, respectively represented by T _mpk = (PG, [s] ₁ , [t] ₂ ) and T _msk = (s, t); where g _s ^x =(g _s ^x1 … g _s ^xn ) ^T , Z _p refers to the set of integers {0,1,2,…,p-1}, and Z _p ⁿ is a set of n-dimensional vectors with domain p.

The authorization server sends the master public key _Tmpk to the edge server.

The method further includes: the edge server and the central server are registered in the blockchain server, the blockchain server generates an edge server public key and an edge server private key for the edge server, and Sending the edge server public key to the central server and sending the edge server private key to the edge server.

The central server and the edge server jointly maintain a global ledger. Successfully registered users can broadcast transactions to the blockchain network and read transactions in the blockchain at any time. The blockchain generates some necessary parameters for registered users, such as public key and private key (edge server public key and edge server private key), where the public key is a public parameter, and the private key is kept and private by the user himself. The edge server public key and the edge server private ^key are represented by ^KNP and _KNS , _respectively .

Referring to Figure 1, the method includes:

S110. The edge server performs functional encryption on the edge data to obtain edge encrypted data, and sends the edge encrypted data to the cloud storage server.

Specifically include:

For the edge data, the edge server randomly selects an integer and an invertible matrix, calculates two column vectors, and further calculates the edge encrypted data according to the two column vectors.

，

，i∈n，则计算得到所述边缘加 密数据为: Specifically, for the edge data x={1, x ₁ ,...x _n }, the edge server randomly selects an integer r∈ Z _p and an invertible matrix A∈GL ₂ , and calculates two column vectors a _i and b _i , where Z _p represents the set of integers, GL ₂ represents the set of 2×2 invertible matrices,

,

, i∈n, then the edge encrypted data is calculated as:

ct=([r] ₁ ,{[a _i ] ₁ ,[b _i ] ₂ } _i∈[n] ).

In some cases, the central server does not need to know all the information of the edge data in the edge server itself, it only needs to know part of the content of the edge data or specific information based on the edge data, and knows that the edge server does not want the central server to know except Content in other edge data unexpected by necessary data. However, in the "central server-edge server" data management system in the related art, key encryption has the characteristics of "all-or-nothing", that is, in the related art, the central server Only all edge data can be obtained, or no edge data can be obtained at all. Obviously, in the related art, the central server also learns the unnecessary edge data, and the data privacy of the edge server cannot be guaranteed.

In the present disclosure, when the edge server encrypts the edge data, the function encryption technology is adopted, and the decryption private key sk _f can be created by using the function f at the same time. When the ciphertext C encrypted by the plaintext m is given, the owner of the private key sk _f can only obtain f(m) through decryption, not m itself, that is, the decryptor can only obtain the specific function of the plaintext, not the complete clear text information. Using the feature of functional encryption, the central server can only obtain the specific information of the edge data of the edge server. Therefore, the edge server can upload its encrypted data without reservation, while ensuring that the central server cannot obtain the complete information of its data. The data privacy of edge servers can be guaranteed.

S120. The edge server constructs data transaction information corresponding to the edge encrypted data, and sends the data transaction information to the blockchain server.

Wherein, the edge server constructs data transaction information corresponding to the edge encrypted data, including:

The edge server retrieves relevant information corresponding to the edge encrypted data and the edge server private key generated by the blockchain server for the edge server, and uses the relevant information and the edge server private key The data transaction information is generated; the related information includes the identifier of the edge server, the identifier of the edge encrypted data, and the time when the edge encrypted data is uploaded to the cloud storage server.

Referring to FIG. 3 , which is a schematic diagram of an algorithm for generating data transaction information according to an embodiment of the present disclosure.

Specifically, it includes: calculating the hash value htx = H(T _info ) of the related information T _info , and using the edge server private key K _A ^S to generate a digital signature Sign(htx) K _A ^S , then obtaining the data transaction information for T _data = {T _info , htx, Sign(htx) K _A ^S }.

Wherein, after the data transaction information is sent to the blockchain server, the method further includes:

the blockchain server broadcasts the data transaction information to the blockchain network of the blockchain server;

The blockchain server verifies the data transaction information using other nodes in the blockchain network, and in response to determining that the data transaction information passes the verification, adds the data transaction information to the blockchain network.

Specifically, it includes: obtaining the edge server public key generated by the blockchain server for the edge server; obtaining the relevant information, the digital signature and the hash value of the relevant information from the data transaction information, and using The edge server public key decrypts the digital signature to generate a hash value for verification, and in response to determining that the hash value of the relevant information is equal to the hash value for verification, the data transaction information passes the verification.

Referring to FIG. 4 , which is a schematic diagram of a data transaction information verification algorithm provided by an embodiment of the present disclosure.

In some embodiments, obtain the edge server public key K _A ^P generated by the blockchain server for the edge server; obtain the related information T _info , the digital signature Sign from the data transaction information T _data (htx) K _A ^S and the hash value htx of the related information T _info , use the edge server public key K _A ^P to decrypt the digital signature Sign (htx) K _A ^S to generate a hash value htx' for verification, In response to determining that the hash value htx of the related information T _info and the verification hash value htx' are equal, the data transaction information passes the verification.

The blockchain is essentially a decentralized distributed ledger, and the mechanism of its chain structure ensures that the transactions on the blockchain are immutable and irreversible. In addition, the decentralized nature of the blockchain can also minimize network paralysis caused by a single point of failure. Using the cryptographic technology and chain structure of the blockchain improves the reliability of the data.

S130. The edge server sends the constructed and trained token generation model to the central server, and the central server uses the token generation model to generate tokens; wherein the token generation model is a machine learning model .

Among them, including:

The edge server sends the token generation model to the authorization server, the authorization server generates a token using the token generation model and the master private key, and sends the token to the service server.

Specifically, the token generation model is expressed as:

f _i ( x )=(P x ) ^T D _i (P x ), ∀ i ∈[ l ],

Among them, i∈[ l ] represents different labels of data x. For example, in handwritten digit recognition, the number displayed on the picture and the font of the number are different labels, that is, different functions of the acquired data x, the matrix P ∈Z _p ^n×d , D _i ∈ Z _p ^{d ×d} .

The service server applies for the token from the authorization server. The authorization server verifies the identity of the service server through the registration information at the authorization server when the service server is created, and after the verification is passed, the authorization server generates the token and sends the token to the service server.

Using the master private key msk and the token generation model _fi , the authorization server generates the token sk _fi :

sk _fi =( f _i [ s , t ] ₂ , f _i ),

where f _i ( s , t )=(P s ) ^T D _i (P t ).

Then, the authorization server sends the token sk _fi =( f _i [ s , t ] ₂ , f _i ) to the service server.

S140. The central server obtains and verifies the data transaction information from the blockchain server, and in response to determining that the data transaction information passes the verification, decrypts the edge obtained from the cloud storage server by using the token Encrypt data to obtain data of a preset range in the edge data.

Among them, including:

The central server decrypts the edge encrypted data by using the master public key and the token to obtain data of a preset range in the edge data.

The business server reads the blockchain ledger, obtains the data transaction information T _data , and verifies whether the transaction has been tampered with, thereby verifying the reliability of the data. The verification process includes: obtaining the edge generated by the blockchain server for the edge server. Server public key K _A ^P ; obtain the related information T _info , the digital signature Sign(htx) K _A ^S and the hash value htx of the related information T _info from the data transaction information T _data , and use the The edge server public key K _A ^P decrypts the digital signature Sign(htx) K _A ^S generates a hash value htx' for verification, in response to determining the hash value htx of the related information T _info and the hash value for verification If the value htx' is equal, the data transaction information passes the verification. After the verification is passed, the service server will perform a decryption operation.

Given the master public key mpk and the encrypted ciphertext of the edge server:

ct=([r] ₁ ,{[a _i ] ₁ ,[b _i ] ₂ } _i∈[n] ), and the token sk _fi =( f _i [ s , t ] ₂ , f _i ) The service server performs a decryption operation.

Among them, the decryption process is:

、

；其中A^-1表示矩 阵A的逆矩阵，P_i表示矩阵P的第i行，s、t表示初始化过程中生成的随机向量，r表示初始化 过程中生成的随机整数； Right, i∈[ d ], compute

,

; where A ^-1 represents the inverse matrix of matrix A, Pi represents the _i -th row of matrix P, s and t represent random vectors generated during initialization, and r represents random integers generated during initialization;

； For i∈[ d ], perform a bilinear mapping operation

;

Among them, because the matrix D _i is a d × d matrix, d represents the number of rows of the matrix D _i ; that is, the number of d is calculated according to the number of rows of the matrix D _i , so the bilinear mapping is also performed. Bilinear mapping.

。并计算

。将上面两个运算结果进行相乘抵消，然后可 以得出

，也即g^fi(x) _T记为out_i； For all i∈[ l ], first perform a linear operation f _i ( s , t )=(P s ) ^T D _i (P t ), and then perform a bilinear mapping operation

. and calculate

. Multiply and cancel the results of the above two operations, and then we can get

, that is, g ^fi(x) _T is denoted as out _i ;

Among them, i∈[ l ] represents the different labels of the edge data x; d _ij represents the elements of the i-th row and j-th column of the matrix D _i ;

，作为 所述边缘数据中的预设范围的数据。 Finally, the service server uses the discrete logarithmic function log to obtain

, as the data in the preset range in the edge data.

It can be seen that the central server can only obtain the specific information of the edge data in the edge server, but cannot obtain all the plaintext of the edge data.

It can be seen from the above that the data transmission method and system based on functional encryption, blockchain and machine learning provided by the present disclosure include: the edge server performs functional encryption on the edge data to obtain the edge encrypted data, and sends the edge encrypted data. to the cloud storage server; the edge server constructs the data transaction information corresponding to the edge encrypted data, and sends the data transaction information to the blockchain server; the edge server sends the constructed and trained token generation model to the central server, and the central server uses The token generation model generates tokens; wherein, the token generation model is a machine learning model; the central server obtains and verifies the data transaction information from the blockchain server, and in response to determining that the data transaction information passes the verification, uses the token to decrypt the data from the cloud storage server The acquired edge encrypted data obtains data of a preset range in the edge data. By combining the related operations of data encryption with the transactions in the blockchain, the reliability of edge data is guaranteed by the inability to tamper with the blockchain.

At the same time, the central server can only know the specific information of the edge data in the edge server, but cannot know all the plaintext of the edge data, and the data privacy of the edge server can be guaranteed.

It should be noted that, the methods of the embodiments of the present disclosure may be executed by a single device, such as a computer or a server. The method in this embodiment can also be applied in a distributed scenario, and is completed by the cooperation of multiple devices. In the case of such a distributed scenario, one device among the multiple devices may only perform one or more steps in the method of the embodiment of the present disclosure, and the multiple devices will interact with each other to complete all the steps. method described.

It should be noted that some embodiments of the present disclosure are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the above-described embodiments and still achieve desirable results. Additionally, the processes depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Referring to FIG. 5 , it is a schematic diagram of an architecture of a data transmission system based on functional encryption, block chain and machine learning provided by an embodiment of the present disclosure. A data transmission system based on functional encryption, blockchain and machine learning, including an edge server, a central server, a blockchain server and a cloud storage server, the system is used to implement the method described above.

The central server is used to manage the edge servers and can request data from the edge servers. The central server includes an authorization server and a business server. The authorization server is used to authenticate and authorize the business server and the edge server, and both the business server and the edge server need to be authenticated and authorized to process business. The business server is used to obtain data from the edge server, and perform data analysis and processing, thereby providing data support for the central server.

The edge server is used to process local services, and local services can be issued or authorized by the central server. The edge server owns local data. For the convenience of distinction, the present disclosure refers to the local data managed and controlled by the edge server as edge data. The edge server can provide edge data to the central server regularly or according to the needs of the central server.

Blockchain servers are used to provide a trusted environment. Blockchain networks are decentralized and independently verifiable, ensuring reliability and accountability. When any node uploads data, it broadcasts the corresponding transaction to the blockchain network. Once the information is recorded on the blockchain, it cannot be tampered with and can resist malicious behavior.

Cloud storage servers are used to provide a data storage platform. The edge server can upload its encrypted edge data to the cloud storage server, and then the central server can freely download the encrypted data. The cloud storage server can relieve the pressure of the local storage, the cloud server itself is not required and it is not allowed to perform any decryption computation.

The edge server, the central server, the blockchain server, and the cloud storage server together constitute an overall architecture for implementing the data transmission method based on functional encryption, blockchain, and machine learning provided by the embodiments of the present disclosure.

Referring to FIG. 6 , which is a more specific schematic diagram of the architecture of the data transmission system based on functional encryption, block chain and machine learning provided by an embodiment of the present disclosure.

The system adopts a three-layer architecture including an application layer, a blockchain layer and a storage layer, the edge server and the central server are arranged in the application layer, and the blockchain server is arranged in the blockchain layer , the cloud storage server is arranged in the storage layer.

In some embodiments, the edge server, the central server, the blockchain server and the cloud storage server are arranged in a three-tier architecture when implementing the method, and the edge server and the central server are arranged at the application layer, so The blockchain server is arranged at the blockchain layer, and the cloud storage server is arranged at the storage layer. The application layer provides the edge server and the central server with the entrance of encryption learning and data analysis, the blockchain layer provides the application layer with the interface to initiate transactions and read transactions, and the storage layer is mainly used to store the data of the application layer.

Application layer: Operations such as authorization and authentication, encryption and decryption, and data training and learning performed by the central server and edge server are all at the application layer. The edge server uploads encrypted data by interacting with the storage layer, and at the same time interacts with the blockchain layer to record related data and store data behavior. The business server downloads encrypted data by interacting with the storage layer, and at the same time interacts with the blockchain layer to verify the reliability of the data.

Blockchain layer: The blockchain layer provides reliability guarantees for data transmission. After the edge server broadcasts the blockchain transaction corresponding to the data to the network, peer nodes in the network verify and record the transaction. The types of transactions in the network mainly include data transactions and reward transactions. Furthermore, nodes in the blockchain are not allowed to learn sensitive information about the data in the application layer.

Among them, the blockchain layer also includes miners and consensus mechanisms. Miners are the foundation of blockchain operation. Without miners, the blockchain cannot function. Miners are not producers of blockchain information, but producers of blocks. Blockchain is an industry that uses blocks as commodities and packs user information into blocks. Users need to write information into the block, and also need to use the information in the block. And miners in the blockchain provide this service. They write information into blocks, so they are sellers in the blockchain marketplace, and users are buyers, and the goods traded are the blockchain. The service of the transaction is to pack user information into blocks. And how miners produce blocks and how to obtain benefits by providing blocks, this mechanism is the consensus mechanism.

Storage layer: The storage layer just plays the role of a storage platform. The storage layer is introduced to save the cost of local storage and blockchain storage. Here, a cloud server is used to store cryptographic data and some computations related to cryptographic data searching.

In some implementations, the present disclosure also defines a threat model.

In order to maximize their profits, potential malicious users may have behaviors that are contrary to system security requirements, and thus have security threats.

Suppose that there is an adversary whose goal is to obtain as much secret information as possible, thereby making more profit. If the adversary is honest but curious, he must trust the mechanisms provided by this disclosure and follow the protocol specifications in the mechanisms provided by this disclosure. The mechanisms provided by the present disclosure allow the adversary to access system public parameters and data streams transmitted in public channels and associated cryptographic algorithms. When an adversary turns into a malicious adversary, in addition to the above capabilities, he can compromise any number of edge servers, eavesdrop on key information, and upload fake data to fool the central server to accomplish his conspiracy. Based on this, information transmission should operate in a secure and trusted channel.

The threat model also makes the following assumptions: by default, the authorization server is completely trusted, and no adversary can compromise the credibility of the authorization server. To do this, permissions can be delimited in the authorization server. Assuming that all authorizations are performed secretly in a safe and efficient manner, the information of the business server will not be leaked to any adversary. There will be no collusion between business servers, so unauthorized business servers cannot obtain data information.

In order to verify the practicability of the present disclosure, deployment and simulation tests of the present disclosure are carried out. The operating system used in the experiment is Linux (5.4.0-62-generic) Ubuntu 18.04.5 installed on VMware Workstation Pro, the memory is 4G, and the device model is Intel(R) Core(TM) i7-9700 CPU @3.00GHz 32G Memory. This disclosure aims to achieve a reliable and conditional privacy-preserving cryptographic learning, so the test includes at least data processing and blockchain interaction.

The experiments utilize the Charm framework, the PBC library, and OpenSSL (version 1.1), where the elliptic curve used is MNT159 with an embedding degree of 6 and 80-bit security. This can be used to implement all encryption algorithms in this disclosure. A blockchain network of five nodes was also deployed based on a simplified toolbox, the language used is Python, the IDE is PyCharm (2020 version), and the code is about 1500 lines of code. The blockchain consensus algorithm is PoW, and the parameters of the genesis block are shown in Table 1 below. In addition, a neural network is trained on TensorFlow to implement the machine learning algorithm. The training dataset is the MNIST handwritten digit set, where the training dataset contains 60,000 samples and the test dataset contains 10,000 samples. Each image in the dataset consists of 28 x 28 pixels, and each pixel is represented by a gray value in the range of 0−255.

Table 1 Parameter settings of the genesis block

parameter trade hash previous block hash serial number value GENESIS BLOCK a5fb4682b627e36c36a55ad6b4c8606465e9723fd48254b92c542e2773c3b05e null 1

The neural network model used in the experiments is a 2-layer fully connected network, the goal is to classify the input as one of 10 numbers in the range 0 - 9, the size of the output layer is set to 10, the number of samples selected for one training ( batch size) is 100.

Referring to FIG. 7 , which is a schematic diagram of a result of a first simulation experiment provided by an embodiment of the present disclosure. a in Figure 7 shows the accuracy at 10 epochs, and as can be seen from a in Figure 7, the training can achieve 97% accuracy. The time cost required for encryption and decryption is tested. Since FE needs to perform time-consuming discrete logarithm and pairing operations during decryption, considering the use of space for time, some discrete logarithms are solved in advance and stored in the database. Here, the PostgreSQL database is used, which is an open source object-relational database system with reliability and better performance. b in Figure 7 and c in Figure 7 show the average time cost of decryption/encryption time as the number of pictures increases, during the experiment, the program will automatically select one of the pictures for encryption and subsequent decryption operations , each encryption/decryption operation is independent and averaged over ten runs.

The interactive performance of the blockchain is also tested. In the blockchain network, the consensus algorithm PoW ensures that only the nodes that solve difficult problems can obtain the accounting right, and the nodes that successfully obtain the accounting right are responsible for recording transaction information, packaging the transaction and storing it. Sync to the entire network.

Referring to FIG. 8 , which is a schematic diagram of a result of a second simulation experiment provided by an embodiment of the present disclosure. A in Figure 8 shows the change of transaction generation time with the increase of data volume. It can be seen that when the data size increases, the time required for transaction generation increases linearly. b in Figure 8 shows the change of transaction confirmation time with the increase of transaction volume in the block. It can be seen that the time consumed by transaction confirmation is very small and has no obvious change. C in Figure 8 shows the change of CPU usage over time. It can be seen that the CPU consumption increases with time, but it is still within an acceptable range in the end. d in Figure 8 shows the change of response time as the number of concurrency increases. It can be seen that the time cost increases with the increase of the number of transactions, but the overall consumption time is shorter and the efficiency is higher.

The above experiments show that the present disclosure also has high accuracy and reasonable throughput under the basic premise of ensuring privacy and reliability.

Based on the same inventive concept and corresponding to any of the above-mentioned embodiments, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, the processor When the program is executed, the data transmission method based on function encryption, block chain and machine learning described in any one of the above embodiments is implemented.

FIG. 9 shows a more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment. The device may include: a processor 1010 , a memory 1020 , an input/output interface 1030 , a communication interface 1040 and a bus 1050 . The processor 1010 , the memory 1020 , the input/output interface 1030 and the communication interface 1040 realize the communication connection among each other within the device through the bus 1050 .

The processor 1010 may be implemented by a general-purpose CPU (Central Processing Unit, central processing unit), a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute related program to implement the technical solutions provided by the embodiments of this specification.

The memory 1020 may be implemented in the form of a ROM (Read Only Memory, read only memory), a RAM (Random Access Memory, random access memory), a static storage device, a dynamic storage device, and the like. The memory 1020 may store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and invoked by the processor 1010 for execution.

The input/output interface 1030 is used to connect the input/output module to realize information input and output. The input/output/module can be configured in the device as a component (not shown in the figure), or can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, and the like.

The communication interface 1040 is used to connect a communication module (not shown in the figure), so as to realize the communication interaction between the device and other devices. The communication module can implement communication through wired means (such as USB, network cable, etc.), or can implement communication through wireless means (such as mobile network, WIFI, Bluetooth, etc.).

The bus 1050 includes a path to transfer information between the various components of the device (eg, the processor 1010, the memory 1020, the input/output interface 1030, and the communication interface 1040).

It should be noted that although the above-mentioned device only shows the processor 1010, the memory 1020, the input/output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include necessary components for normal operation. other components. In addition, those skilled in the art can understand that, the above-mentioned device may only include components necessary to implement the solutions of the embodiments of the present specification, rather than all the components shown in the figures.

The electronic device in the above embodiment is used to implement the corresponding data transmission method based on function encryption, block chain and machine learning in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

Based on the same inventive concept and corresponding to any of the above-mentioned embodiments, the present disclosure also provides a non-transitory computer-readable storage medium, where the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions use In order to make the computer execute the data transmission method based on functional encryption, block chain and machine learning as described in any of the above embodiments.

The computer readable medium of this embodiment includes both permanent and non-permanent, removable and non-removable media and can be implemented by any method or technology for information storage. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cartridges, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the data transmission method based on functional encryption, block chain and machine learning as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments , and will not be repeated here.

It should be noted that the embodiments of the present disclosure can also be further described in the following ways:

A data transmission method based on functional encryption, blockchain and machine learning, the method is implemented by an edge server, a central server, a blockchain server and a cloud storage server, and the method includes:

The edge server performs functional encryption on the edge data to obtain edge encrypted data, and sends the edge encrypted data to the cloud storage server;

The edge server constructs data transaction information corresponding to the edge encrypted data, and sends the data transaction information to the blockchain server;

The edge server sends the constructed and trained token generation model to the central server, and the central server uses the token generation model to generate tokens; wherein the token generation model is a machine learning model;

The central server obtains and verifies the data transaction information from the blockchain server, and in response to determining that the data transaction information passes the verification, decrypts the edge encrypted data obtained from the cloud storage server by using the token , to obtain data of a preset range in the edge data.

Optionally, the method further includes: the central server generates a master public key and a master private key, and sends the master public key to the edge server.

Optionally, it further includes: the edge server and the central server are registered in the blockchain server, the blockchain server generates an edge server public key and an edge server private key for the edge server, and Sending the edge server public key to the central server and sending the edge server private key to the edge server.

Optionally, the edge server performs functional encryption on edge data to obtain edge encrypted data, and sends the edge encrypted data to the cloud storage server, including:

For the edge data, the edge server randomly selects an integer and an invertible matrix, calculates two column vectors, and further calculates the edge encrypted data according to the two column vectors.

Optionally, wherein the edge server constructs data transaction information corresponding to the edge encrypted data, including:

The edge server retrieves relevant information corresponding to the edge encrypted data and the edge server private key generated by the blockchain server for the edge server, and uses the relevant information and the edge server private key The data transaction information is generated; the related information includes the identifier of the edge server, the identifier of the edge encrypted data, and the time when the edge encrypted data is uploaded to the cloud storage server.

Optionally, after the edge server sends the data transaction information to the blockchain server, it further includes:

the blockchain server broadcasts the data transaction information to the blockchain network of the blockchain server;

The blockchain server verifies the data transaction information using other nodes in the blockchain network, and in response to determining that the data transaction information passes the verification, adds the data transaction information to the blockchain network.

Optionally, the central server includes an authorization server and a service server; the edge server sends the constructed and trained token generation model to the central server, and the central server uses the token generation model Generate tokens, including:

The edge server sends the token generation model to the authorization server, the authorization server generates a token using the token generation model and the master private key, and sends the token to the service server.

Optionally, the central server obtains the data transaction information from the blockchain server and verifies it, and in response to determining that the data transaction information passes the verification, decrypts the edge encrypted data by using the token, and obtains: The data of the preset range in the edge data includes:

The central server decrypts the edge encrypted data by using the master public key and the token to obtain data of a preset range in the edge data.

A data transmission system based on functional encryption, block chain and machine learning, including an edge server, a central server, a block chain server and a cloud storage server, the system is used to implement the above method.

Optionally, the system adopts a three-layer architecture including an application layer, a blockchain layer and a storage layer, the edge server and the central server are arranged in the application layer, and the blockchain server is arranged in the In the blockchain layer, the cloud storage server is arranged in the storage layer.

Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is only exemplary, and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; under the spirit of the present disclosure, the above embodiments or Technical features in different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the disclosed embodiments as described above, which are not provided in detail for the sake of brevity.

In addition, to simplify illustration and discussion, and in order not to obscure the embodiments of the present disclosure, well-known power/power sources associated with integrated circuit (IC) chips and other components may or may not be shown in the figures provided in the figures provided. ground connection. Furthermore, devices may be shown in block diagram form in order to avoid obscuring the disclosed embodiments, and this also takes into account the fact that details regarding the implementation of these block diagram devices are highly dependent on the implementation of the disclosed embodiments platform (ie, these details should be well within the understanding of those skilled in the art). Where specific details (eg, circuits) are set forth to describe exemplary embodiments of the present disclosure, it will be apparent to those skilled in the art that these specific details may be made without or with changes The embodiments of the present disclosure are implemented as follows. Accordingly, these descriptions are to be considered illustrative rather than restrictive.

Although the present disclosure has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations to these embodiments will be apparent to those of ordinary skill in the art from the foregoing description. For example, other memory architectures (eg, dynamic RAM (DRAM)) may use the discussed embodiments.

The disclosed embodiments are intended to cover all such alternatives, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present disclosure should be included within the protection scope of the present disclosure.

Claims (10)

1. A data transmission method based on function encryption, blockchain and machine learning, the method is realized by an edge server, a center server, a blockchain server and a cloud storage server, and the method comprises the following steps:

the edge server performs function encryption on edge data to obtain edge encrypted data, and sends the edge encrypted data to the cloud storage server;

the edge server constructs data transaction information corresponding to the edge encrypted data and sends the data transaction information to the block chain server;

the edge server sends the constructed and trained token generation model to the central server, and the central server generates a token by using the token generation model; wherein the token generation model is a machine learning model;

and the central server acquires and verifies the data transaction information from the block chain server, and decrypts the edge encrypted data acquired from the cloud storage server by using the token in response to the fact that the data transaction information is verified to obtain data in a preset range in the edge data.

2. The method of claim 1, further comprising: and the central server generates a main public key and a main private key and sends the main public key to the edge server.

3. The method of claim 1, further comprising: the edge server and the central server register in the blockchain server, and the blockchain server generates an edge server public key and an edge server private key for the edge server, and sends the edge server public key to the central server and the edge server private key to the edge server.

4. The method according to claim 1, wherein the edge server performs function encryption on edge data to obtain edge encrypted data, and sends the edge encrypted data to the cloud storage server, and the method comprises:

and for the edge data, the edge server randomly selects an integer and a reversible matrix, calculates to obtain two column vectors, and further calculates to obtain the edge encryption data according to the two column vectors.

5. The method of claim 3, wherein the edge server constructs data transaction information corresponding to the edge encrypted data, comprising:

the edge server calls relevant information corresponding to the edge encrypted data and the edge server private key generated by the blockchain server aiming at the edge server, and generates the data transaction information by using the relevant information and the edge server private key; the related information comprises the identification of the edge server, the identification of the edge encrypted data and the time for uploading the edge encrypted data to the cloud storage server.

6. The method of claim 1, wherein after the edge server sends the data transaction information to the blockchain server, further comprising:

the blockchain server broadcasts the data transaction information to a blockchain network of the blockchain server;

the blockchain server verifies the data transaction information with other nodes in the blockchain network and adds the data transaction information to the blockchain network in response to determining that the data transaction information is verified.

7. The method of claim 2, wherein the central server comprises an authorization server and a business server; the edge server sends the constructed and trained token generation model to the central server, and the central server generates a token by using the token generation model, including:

and the edge server sends the token generation model to the authorization server, and the authorization server generates a token by using the token generation model and the main private key and sends the token to the service server.

8. The method of claim 2, wherein the central server obtains and verifies the data transaction information from the blockchain server, and in response to determining that the data transaction information is verified, decrypts the edge encrypted data using the token to obtain a preset range of data in the edge data, including:

and the central server decrypts the edge encrypted data by using the main public key and the token to obtain the data in the preset range in the edge data.

9. A data transmission system based on function encryption, blockchain and machine learning, comprising edge servers, central servers, blockchain servers and cloud storage servers, the system being configured to implement the method according to any one of claims 1 to 8.

10. The system of claim 9, wherein the system employs a three-tier architecture comprising an application tier, a blockchain tier, and a storage tier, the edge servers and the central server being disposed at the application tier, the blockchain servers being disposed at the blockchain tier, and the cloud storage servers being disposed at the storage tier.

Images