Business data protection method and system based on block chain

Abstract

The invention belongs to the technical field of data protection, and discloses a business data protection method and system based on a block chain. The method comprises the following steps: constructing a block chain network, a Hfish honeypot chain network, a data security classification model and an abnormal traffic detection model based on a cloud data center, and carrying out key generation and identity registration on a data acquisition device; encrypting and signing real-time service data based on a data acquisition device, and uploading the real-time service data to a cloud data center; performing signature verification and decryption based on the cloud data center; and carrying out data security classification and uplink storage on the decrypted real-time service data, capturing real-time traffic data, and carrying out abnormal traffic detection on the real-time traffic data. According to the invention, the problems of high hardware cost, low storage reliability and low data security in the prior art are solved.

Description

Technical Field

[0001] The present invention belongs to the technical field of data protection, and particularly relates to a business data protection method and system based on blockchain. Background Art

[0002] Business data is the core data of an enterprise, including important information such as partners, supply chains, and trade data. With the growth of the enterprise's scale, the volume of business data has increased exponentially. Existing business data is often stored in an enterprise's local database, which is prone to data loss due to hardware crashes, has high hardware costs, and low storage reliability. The protection level of the local database is low and it cannot effectively defend against malicious attacks, resulting in low data security. Summary of the Invention

[0003] In order to solve the problems of high hardware costs, low storage reliability, and low data security existing in the prior art, the purpose of the present invention is to provide a business data protection method and system based on blockchain.

[0004] The technical solution adopted by the present invention is as follows:

[0005] A business data protection method based on blockchain, comprising the following steps:

[0006] Based on a cloud data center, construct a blockchain network, an Hfish honeypot chain network, a data classification model for data confidentiality levels, and an abnormal traffic detection model, and perform key generation and identity registration on all data collection devices connected to the cloud data center to obtain the public-private key pairs and signature information of each data collection device;

[0007] Based on the data collection device, and according to the private key and signature information in the public-private key pair, encrypt and sign the collected real-time business data to obtain the corresponding encrypted real-time business data and real-time signature data, and upload them to the cloud data center;

[0008] Based on the cloud data center, call a trusted institution to verify the signature of the real-time signature data. After the signature verification passes, decrypt the encrypted real-time business data according to the public key in the public-private key pair of the data collection device to obtain the corresponding decrypted real-time business data;

[0009] Use the data classification model for data confidentiality levels to classify the decrypted real-time business data to obtain the corresponding real-time data classification results for data confidentiality levels. Use the blockchain network to store the decrypted real-time business data and the real-time data classification results for data confidentiality levels on the blockchain. Use the Hfish honeypot chain network to capture the real-time traffic data of the data collection device, and use the abnormal traffic detection model to detect abnormal traffic in the real-time traffic data to obtain the corresponding real-time abnormal traffic detection results.

[0010] Further, based on the cloud data center, a blockchain network, an Hfish honeypot chain network, a data classification model, and an abnormal traffic detection model are constructed, and key generation and identity registration are performed on all data acquisition devices connected to the cloud data center to obtain the public-private key pairs and signature information of each data acquisition device, including the following steps:

[0011] Based on the cloud data center, a management server node, a smart contract, an IFPS system, and several data server nodes are deployed to construct a blockchain network;

[0012] Based on the blockchain network, an Hfish management module is deployed in the management server node, and an Hfish honeypot is deployed in each data server node to construct an Hfish honeypot chain network;

[0013] According to a number of historical business data, a data classification model is constructed using a deep learning algorithm, and the data classification model is deployed to the management server node;

[0014] According to a number of historical traffic data, an abnormal traffic detection model is constructed using a deep learning algorithm, and the abnormal traffic detection model is deployed in the Hfish management module;

[0015] Collect the attribute information and entity IDs of all data acquisition devices connected to the cloud data center, and send a number of attribute information and a number of entity IDs to a trusted institution;

[0016] Based on the trusted institution, key generation and identity registration are performed on the data acquisition device according to the attribute information and entity ID to obtain the corresponding public-private key pairs and signature information;

[0017] Send the private key in the public-private key pair and the signature information to the corresponding data acquisition device, and publish the public key in the public-private key pair to the cloud data center.

[0018] Further, based on the cloud data center, a management server node, a smart contract, an IFPS system, and several data server nodes are deployed to construct a blockchain network, including the following steps:

[0019] Based on the cloud data center, several distributed-connected data server nodes are deployed, and the network performance parameters of each data server node are collected;

[0020] According to the network performance parameters and network requirements, select the data server node with the best network among several data server nodes as the management server node;

[0021] Connect the management server node to the IFPS system, deploy the smart contract, and construct a blockchain network.

[0022] Further, according to the network performance parameters and network requirements, the IPCO algorithm is used to select the data server node with the optimal network among several data server nodes as the management server node.

[0023] Further, the data classification model of confidentiality level is constructed based on the N-GAN-MLP algorithm, where N is the total number of dimensions of data confidentiality level concerned.

[0024] Further, based on the blockchain network, the Hfish management module is deployed in the management server node, and the Hfish honeypot is deployed in each data server node to construct the Hfish honeypot chain network, including the following steps:

[0025] Based on the blockchain network, according to the network performance parameters of the management server node, the Hfish management module is deployed in the management server node;

[0026] According to the server system parameters of each data server node, the corresponding Hfish honeypot elements are generated, and according to the Hfish honeypot elements, the Hfish honeypot is deployed in the data server node;

[0027] A traffic probe is set in each Hfish honeypot, and all traffic probes are connected to the Hfish management module.

[0028] Further, according to a number of historical traffic data, a deep learning algorithm is used to construct an abnormal traffic detection model, and the abnormal traffic detection model is deployed in the Hfish management module, including the following steps:

[0029] Collect a number of historical traffic data, and preprocess the number of historical traffic data to obtain a number of preprocessed historical traffic data;

[0030] According to a number of preprocessed historical traffic data, a deep learning algorithm is used to construct an abnormal traffic detection model;

[0031] The abnormal traffic detection model is deployed in the Hfish management module, and the input end of the abnormal traffic detection model is connected to all traffic probes.

[0032] Further, the abnormal traffic detection model is constructed based on the RF-BiLSTM algorithm.

[0033] Further, use a data classification model for data confidentiality levels to classify the decrypted real-time business data into corresponding real-time data confidentiality level classification results. Use a blockchain network to store the decrypted real-time business data and the real-time data confidentiality level classification results on the chain. Use the Hfish honeypot chain network to capture the real-time traffic data of the data acquisition device, and use an abnormal traffic detection model to detect abnormal traffic in the real-time traffic data to obtain corresponding real-time abnormal traffic detection results, including the following steps:

[0034] Based on the management server node of the blockchain network, use a data classification model for data confidentiality levels to classify the decrypted real-time business data into corresponding real-time data confidentiality level classification results;

[0035] Based on the management server node, store the decrypted real-time business data and the real-time data confidentiality level classification results, and generate corresponding real-time business data hash values;

[0036] Invoke a smart contract to convert the real-time business data hash value into a real-time data block, generate a corresponding real-time data storage request, and send it to several data server nodes of the blockchain network;

[0037] Based on several data server nodes, use the PBFT consensus algorithm to conduct consensus on the intellectual property certification request. After successful consensus, link and store the real-time data block on the chain;

[0038] Use the traffic probe of the Hfish honeypot in the Hfish honeypot chain network to capture the real-time traffic data of the data acquisition device and send it to the abnormal traffic detection model of the Hfish management module;

[0039] Use an abnormal traffic detection model to detect abnormal traffic in the real-time traffic data to obtain corresponding real-time abnormal traffic detection results;

[0040] If the real-time abnormal traffic detection result indicates the existence of abnormal traffic, use a firewall to block the corresponding data acquisition device and add it to the blacklist.

[0041] A business data protection system based on blockchain is used to implement a business data protection method. The system includes a cloud data center, a trusted institution, and several data acquisition devices. The cloud data center and the trusted institution are both respectively communicatively connected to the several data acquisition devices, and the trusted institution is communicatively connected to the cloud data center;

[0042] The cloud data center includes an initialization unit, a data decryption unit, a data classification unit for data confidentiality levels, an on-chain storage unit, and an abnormal traffic detection unit.

[0043] The beneficial effects of the present invention are:

[0044] The present invention discloses a method and system for protecting business data based on blockchain. By combining a blockchain network, an Hfish honeypot chain network, a data classification model based on data confidentiality levels, and an abnormal traffic detection model, all-round protection of business data is achieved. Based on a cloud data center, unified storage and management of the business center are carried out, reducing the investment in hardware costs while improving the convenience of business data management and data value, and being more applicable to enterprise application scenarios with a large volume of business data. By utilizing the characteristics of blockchain such as decentralization and immutability, the authenticity and integrity of business data are ensured, and the reliability of data storage is improved. By creating an Hfish honeypot chain network to attract attackers, important data in the cloud data center is protected from attacks, improving the security of data storage and the protection level of the cloud data center. By combining encryption technology and digital identity technology, data security is further improved to prevent data leakage. Abnormal detection of traffic accessing the cloud data center is carried out to promptly detect malicious attacks, further improving data security.

[0045] Other beneficial effects of the present invention will be further described in the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flowchart of the method for protecting business data based on blockchain in the present invention.

[0047] Figure 2 is a structural block diagram of the system for protecting business data based on blockchain in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0048] The present invention will be further explained below with reference to the accompanying drawings and specific embodiments.

[0049] Embodiment 1:

[0050] As Figure 1 shown, this embodiment provides a method for protecting business data based on blockchain, including the following steps:

[0051] S1: Based on the cloud data center, construct a blockchain network, an Hfish honeypot chain network, a data classification model based on data confidentiality levels, and an abnormal traffic detection model, and perform key generation and identity registration for all data collection devices connected to the cloud data center to obtain the public-private key pairs and signature information of each data collection device, including the following steps:

[0052] S1-1: Based on the cloud data center, deploy a management server node, a smart contract, an IFPS system, and several data server nodes to construct a blockchain network, including the following steps:

[0053] S1-1-1: Based on the cloud data center, deploy several data server nodes with distributed connections, and collect the network performance parameters of each data server node;

[0054] S1-1-2: According to the network performance parameters and network requirements, use the Improved Crested Porcupine Optimizer (ICPO) algorithm to select the data server node with the optimal network among several data server nodes as the management server node, including the following steps:

[0055] S1-1-2-1: According to the network performance parameters and network requirements, set the optimization objective and fitness function of the IPCO algorithm;

[0056] The formula is:

[0057]

[0058] In the formula, F is the optimization objective set according to the network requirements; GL{*} is the objective function obtained according to the network performance parameters; is the communication length cost function of the IPCO individual x; is the resource consumption cost function of the IPCO individual x; is the communication time cost function of the IPCO individual x;

[0059]

[0060] In the formula, f(x) is the fitness function of the IPCO individual x; α, β, are all weight coefficients;

[0061] S1-1-2-2: Encode the IP addresses of several data server nodes as the positions of the IPCO individuals of the IPCO algorithm;

[0062] S1-1-2-3: Set the algorithm parameters and the maximum number of iterations of the IPCO algorithm;

[0063] S1-1-2-4: According to the number of individuals in the algorithm parameters, use the Circle chaotic mapping sequence for initialization to obtain the initial IPCO population;

[0064] The formula is:

[0065]

[0066] In the formula, is the initial IPCO individual of the Circle chaotic mapping; is the randomly generated initial IPCO individual; i' is the IPCO individual indicator; mod(*) is the remainder function;

[0067] S1-1-2-5: Introduce a cyclic population reduction mechanism to limit the number of individuals in the algorithm parameters and obtain the updated algorithm parameters for the next iteration;

[0068] The formula is:

[0069]

[0070] In the formula, S t+1 is the number of individuals in the IPCO population parameter for the (t + 1)-th iteration; S t is the number of individuals in the IPCO population parameter for the t-th iteration; S min is the minimum value of the number of individuals in the IPCO population parameter; a' is the function evaluation parameter; V is the function evaluation loop parameter; V max is the maximum function evaluation loop parameter;

[0071] S1-1-2-6: Calculate the initial fitness value of the initial IPCO individuals in the initial IPCO population according to the fitness function;

[0072] S1-1-2-7: Update the initial IPCO population using the first defense strategy, the second defense strategy, the third defense strategy, and the fourth defense strategy according to the initial fitness value and the updated algorithm parameters to obtain the updated IPCO population;

[0073] The formula for the first defense strategy is:

[0074]

[0075] In the formula, is the updated IPCO individual within the first defense range; is the initial IPCO individual within the first defense range; τ 1 is a random number based on the normal distribution; τ 2 is a random value within the interval [0, 1]; is the optimal solution within the first defense range; is the vector generated between the true optimal solution and the randomly selected optimal solution from the IPCO population within the first defense range; i' is the IPCO individual indicator; t is the iteration indicator;

[0076] The formula for the second defense strategy is:

[0077]

[0078] In the formula, is the updated IPCO individual within the second defense range; is the initial IPCO individual within the second defense range; is the search upper limit vector for the second defense range; τ 3 is a random value in the interval [0, 1]; are the r1-th and r2-th initial IPCO individuals respectively; r1 and r2 are both two random integers between [1, S]; is the vector generated between the true optimal solution and the randomly selected optimal solution from the IPCO population within the second defense range;

[0079] The formula for the third defense strategy is:

[0080]

[0081] In the formula, is the updated IPCO individual within the third defense range; is the initial IPCO individual within the third defense range; is the search upper limit vector for the third defense range; are the r2-th and r3-th initial IPCO individuals respectively; r3 is a random integer between [1, S]; is the odor diffusion factor defined by the fitness function; λ t is the defense factor; is the search direction control parameter;

[0082] The formula for the fourth defense strategy is:

[0083]

[0084] In the formula, is the updated IPCO individual within the fourth defense range; is the initial IPCO individual within the fourth defense range; is the optimal solution within the fourth defense range; τ 4 and τ 5 are both random values in the interval [0, 1]; λ t is the defense factor; is the search direction control parameter; is the average force affecting the search direction; a' is the convergence speed factor;

[0085] S1-1-2-8: Use the dynamic reverse learning algorithm to perform dynamic reverse learning on the updated IPCO population to generate a dynamically reversed IPCO population;

[0086] The formula is:

[0087]

[0088] In the formula, is a dynamically reversed IPCO individual; γ is a decreasing inertia coefficient; L max and L min are the maximum and minimum values of the vector space respectively; is the updated IPCO individual;

[0089] S1-1-2-9: According to the fitness function, calculate the fitness values of all IPCO individuals in the updated IPCO population and the dynamically reversed IPCO population, and take the IPCO individual with the minimum fitness value as the optimal individual;

[0090] S1-1-2-10: If the number of iterations reaches the maximum number of iterations or the fitness value of the optimal individual meets the requirements, then output the optimal solution corresponding to the current optimal individual to obtain the IP address of the optimal data server node, that is, the IP address of the management server node;

[0091] S1-1-3: Connect the management server node to the InterPlanetary File System (IPFS), deploy smart contracts, and build a blockchain network;

[0092] S1-2: Based on the blockchain network, deploy the Hfish management module in the management server node and deploy Hfish honeypots in each data server node to build an Hfish honeypot chain network, including the following steps:

[0093] S1-2-1: Based on the blockchain network, deploy the Hfish management module in the management server node according to the network performance parameters of the management server node;

[0094] S1-2-2: Generate corresponding Hfish honeypot elements according to the server system parameters of each data server node, and deploy Hfish honeypots in the data server nodes according to the Hfish honeypot elements;

[0095] The key to deploying the Hfish honeypot is to deploy the corresponding virtual server in the cloud data center, and through the virtual server, realize the simulation of the data server node; The Hfish honeypot elements include the service framework protocol for building the virtual server corresponding to the Hfish honeypot, the virtual server attribute information, and the server system attribute information;

[0096] S1-2-3: Set traffic probes in each Hfish honeypot and connect all traffic probes to the Hfish management module;

[0097] S1-3: According to a number of historical business data, use a deep learning algorithm to build a data classification model for data classification levels, and deploy the data classification model for data classification levels to the management server node, including the following steps:

[0098] S1-3-1: Collect a number of historical business data, and preprocess the number of historical business data to obtain a number of preprocessed historical business data;

[0099] S1-3-3: According to a number of preprocessed historical business data, use deep learning algorithms to build a data classification model;

[0100] The data classification model is built based on the N-Generative Adversarial Network (GAN)-Multilayer Perceptron (MLP) algorithm, where N is the total number of data classification attention dimensions, and the data classification model includes N-dimensional feature extraction modules built based on the GAN algorithm and data classification modules built based on the MLP algorithm;

[0101] The data classification attention dimensions include dimensions such as the number of confidential words, the degree of confidentiality, and the value of business data;

[0102] The GAN network includes a generator and a discriminator. The generator is responsible for generating business data features from the latent space, and the discriminator is responsible for judging the authenticity of business data features. The identification of business data is added to the discriminator, so that it not only judges the authenticity of business data, but also judges whether it conforms to business data features. By extracting the features of business data from different dimensions, multi-angle analysis is realized, the comprehensiveness of data classification is improved, the MLP network fuses the multi-angle business data features, improves the representation ability of business data features for data information, and improves the accuracy of data classification;

[0103] S1-3-4: Deploy the data classification model to the management server node;

[0104] S1-4: According to a number of historical traffic data, use deep learning algorithms to build an abnormal traffic detection model, and deploy the abnormal traffic detection model in the Hfish management module, including the following steps:

[0105] S1-4-1: Collect a number of historical traffic data, and preprocess the number of historical traffic data to obtain a number of preprocessed historical traffic data;

[0106] S1-4-3: According to a number of preprocessed historical traffic data, use deep learning algorithms to build an abnormal traffic detection model;

[0107] The abnormal traffic detection model is constructed based on the Random Forest (RF)-Bidirectional Long Short-Term Memory (BiLSTM) algorithm, and the abnormal traffic detection model includes a traffic key feature screening module constructed based on the RF algorithm and an abnormal traffic detection module constructed based on the BiLSTM algorithm;

[0108] The RF module screens key features of the input traffic data through the internal ClassificationAnd RegressionTree (CART) to extract key traffic features related to behaviors for subsequent abnormal judgment. The BiLSTM network learns the features of abnormal behavior traffic through a deep structure to achieve the detection of abnormal traffic;

[0109] S1-4-4: Deploy the abnormal traffic detection model in the Hfish management module and connect the input end of the abnormal traffic detection model to all traffic probes;

[0110] S1-5: Collect the attribute information and entity IDs of all data collection devices connected to the cloud data center and send a number of attribute information and a number of entity IDs to a trusted institution;

[0111] S1-6: Based on the trusted institution, generate keys and register identities for the data collection devices according to the attribute information and entity IDs to obtain corresponding public-private key pairs and signature information, including the following steps:

[0112] S1-6-1: Based on the trusted institution, use an asymmetric encryption algorithm to generate keys according to the attribute information of the data collection device to obtain public parameters GP, a master secret key MSK, and an initial key PK;

[0113] The formula is:

[0114]

[0115] In the formula, GP is the public parameter; MSK is the master secret key; PK is the initial key; a is a random number in the integer domain Z p ; H 1 、H 2 、H 3 、H 4 、H 5 、H 6 、H u are all target hash functions; g, g 1 、g a are all random numbers of the generators of the cyclic group G; e(g,g) a is the bilinear mapping of the random number g;

[0116] S1-6-2: Generate the public-private key pair for the corresponding data acquisition device according to the public parameter GP, the master secret key MSK, the initial key PK, and the attribute information V of the data acquisition device u , and the public-private key pair includes the private key SK u and the public key PK u , and the formula is:

[0117] SK u = {MSK, V u , K = g a g ab , L u = g b , (K = H 3 (V u )) b )}

[0118]

[0119] In the formula, SK u is the private key of the data acquisition device u; b is a random number in the integer domain Z p ; L u , K are the private key parameters of the data acquisition device u; H 3 is the target hash function of the public parameter GP; u is the data acquisition device indicator; MSK is the master secret key; PK is the initial key; PK u is the public key of the data acquisition device u; g b , g a , g ab are random numbers of the generators of the cyclic group G; V u is the attribute information of the data acquisition device u;

[0120] S1-6-3: Perform identity registration according to the private key in the public-private key pair and the corresponding entity ID to obtain the signature information of the corresponding data acquisition device;

[0121] The formula is:

[0122]

[0123] In the formula, k' is a random number; K u is the registration parameter of the data acquisition device u; KID u is the registration ID of the data acquisition device u; KID u and the corresponding K u constitute the signature information {K u , KID u}; H 1 is the target hash function; ID uis the entity ID of the data acquisition device u; SK u is the private key of the data acquisition device u; is the prime order; P is the prime field base point;

[0124] S1-7: Send the private key and signature information in the public-private key pair to the corresponding data acquisition device, and publish the public key in the public-private key pair to the cloud data center;

[0125] S2: Based on the data acquisition device, and according to the private key and signature information in the public-private key pair, encrypt and sign the collected real-time service data to obtain the corresponding encrypted real-time service data and real-time signature data, and upload them to the cloud data center;

[0126] The formula is:

[0127] M u = E(SK u , m u )

[0128] In the formula, M u is the encrypted real-time service data of the data acquisition device u; E(*) is the asymmetric encryption function; m u is the real-time service data of the data acquisition device u; SK u is the private key of the data acquisition device u; u is the data acquisition device indicator;

[0129] The formula is:

[0130]

[0131] In the formula, r' is a random number; is the prime order; P is the prime field base point; H 2 is the target hash function; K u is the registration parameter of the data acquisition device u in the signature information {K u , KID u}; KID u is the registration ID of the data acquisition device u in the signature information {K u , KID u}; ID u is the entity ID of the data acquisition device u; The signature data formed is {ID u , M u , γ' = {K u , R u , B u}}; R u , B u , γ' are all signature parameters of the data acquisition device u;

[0132] S3: Based on the cloud data center, call a trusted institution to verify the signature of the real-time signature data. After the signature verification passes, decrypt the encrypted real-time service data according to the public key in the public-private key pair of the data acquisition device to obtain the corresponding decrypted real-time service data;

[0133] The formula is:

[0134] β u B u P = β u H 2 (R u ,M u ,ID u ,K u )R u +β u K u +β u H 1 (ID u ,K u )PK u

[0135] In the formula, β u is the signature verification parameter of the data acquisition device u; PK u is the public key of the data acquisition device u; if the left side of the equation is equal to the right side, the signature verification passes;

[0136] S4: Use the data classification model of data confidentiality levels to classify the decrypted real-time service data to obtain the corresponding real-time data classification results of data confidentiality levels. Use the blockchain network to store the decrypted real-time service data and the real-time data classification results of data confidentiality levels on the chain. Use the Hfish honeypot chain network to capture the real-time traffic data of the data acquisition device, and use the abnormal traffic detection model to detect the abnormal traffic of the real-time traffic data to obtain the corresponding real-time abnormal traffic detection results, including the following steps:

[0137] S4-1: Based on the management server node of the blockchain network, use the data classification model of data confidentiality levels to classify the decrypted real-time service data to obtain the corresponding real-time data classification results of data confidentiality levels, including the following steps:

[0138] S4-1-1: Based on the management server node of the blockchain network, use the N-dimensional feature extraction module of the data classification model of data confidentiality levels to extract the N real-time dimensional features of the decrypted real-time service data;

[0139] S4-1-2: Use the data classification module of data confidentiality levels to perform feature fusion on the N real-time dimensional features to obtain the corresponding real-time fusion features;

[0140] S4-1-3: Classify the data confidentiality level according to the real-time fusion features to obtain the corresponding real-time data confidentiality level classification result;

[0141] S4-2: Based on the management server node, store the decrypted real-time service data and the real-time data confidentiality level classification result, and generate the corresponding real-time service data hash value;

[0142] S4-3: Invoke the smart contract, convert the real-time service data hash value into a real-time data block, generate the corresponding real-time data storage request, and send it to several data server nodes of the blockchain network;

[0143] S4-4: Based on several data server nodes, use the Practical Byzantine Fault Tolerance (PBFT) consensus algorithm to consensus on the intellectual property authentication request. After successful consensus, link and chain the real-time data block;

[0144] S4-5: Use the traffic probe of the Hfish honeypot in the Hfish honeypot chain network to capture the real-time traffic data of the data acquisition device and send it to the abnormal traffic detection model of the Hfish management module;

[0145] S4-6: Use the abnormal traffic detection model to detect the abnormal traffic of the real-time traffic data to obtain the corresponding real-time abnormal traffic detection result, including the following steps:

[0146] S4-6-1: Use the trained RF structure in the traffic key feature screening module to extract the feature contribution degrees of several real-time alternative features in the real-time traffic data;

[0147] The formula is:

[0148]

[0149] In the formula, is the feature contribution degree of the j-th real-time alternative feature; is the feature contribution degree of the j-th alternative feature in the i-th tree of the random forest; i is the CART tree indicator; j is the alternative feature indicator; n is the total number of CARTs;

[0150]

[0151] In the formula, GI m 、GI l 、GI r are the Gini indices of the CART tree nodes m, l, and r of the random forest; p mkis the proportion of category k in CART tree node m; K is the total number of categories; m, l, r are node indicators; k is a category indicator; K is the total number of categories;

[0152] S4-6-2: Normalize the feature contribution degrees of several real-time alternative features to obtain the corresponding normalized feature contribution degrees;

[0153] The formula is:

[0154]

[0155] In the formula, VIM j is the normalized feature contribution degree; J is the total number of real-time alternative features;

[0156] S4-6-3: Generate the feature selection standard values of several real-time alternative features according to the normalized feature contribution degrees;

[0157] The formula is:

[0158]

[0159] In the formula, CFC j is the feature selection standard value of the j-th real-time alternative feature; VIM j' is the normalized feature contribution degree of the j'-th real-time alternative feature; j' is an alternative feature indicator;

[0160] S4-6-4: Sort the real-time alternative features in descending order according to the feature selection standard values, and select the first M real-time alternative features as key features to obtain M real-time key features, where M is the total number of real-time key features;

[0161] S4-6-5: Use the abnormal traffic detection module to perform abnormal traffic detection based on the M real-time key features to obtain the corresponding real-time abnormal traffic detection results;

[0162] S4-7: If the real-time abnormal traffic detection result indicates the existence of abnormal traffic, use the firewall to block the corresponding data acquisition device and add it to the blacklist.

[0163] Embodiment 2:

[0164] As Figure 2 shown, this embodiment provides a blockchain-based business data protection system for implementing the business data protection method. The system includes a cloud data center, a trusted institution, and several data acquisition devices. The cloud data center and the trusted institution are respectively communicatively connected to several data acquisition devices, and the trusted institution is communicatively connected to the cloud data center;

[0165] A trusted institution for generating keys and registering the identities of all data collection devices connected to the cloud data center, obtaining the public-private key pairs and signature information of each data collection device;

[0166] A data collection device for encrypting and signing the collected real-time service data according to the private key in the public-private key pair and the signature information, obtaining the corresponding encrypted real-time service data and real-time signature data, and uploading them to the cloud data center;

[0167] The cloud data center includes an initialization unit, a data decryption unit, a data classification unit for data classification levels, an on-chain storage unit, and an abnormal traffic detection unit;

[0168] The initialization unit for constructing a blockchain network, an Hfish honeypot chain network, a data classification model for data classification levels, and an abnormal traffic detection model;

[0169] The data decryption unit for calling the trusted institution to verify the signature of the real-time signature data. After the signature verification passes, decrypt the encrypted real-time service data according to the public key in the public-private key pair of the data collection device to obtain the corresponding decrypted real-time service data;

[0170] The data classification unit for data classification levels for classifying the decrypted real-time service data using the data classification model for data classification levels to obtain the corresponding real-time data classification results for data classification levels;

[0171] The on-chain storage unit for storing the decrypted real-time service data and the real-time data classification results for data classification levels on the blockchain using the blockchain network;

[0172] The abnormal traffic detection unit for capturing the real-time traffic data of the data collection device using the Hfish honeypot chain network and detecting abnormal traffic in the real-time traffic data using the abnormal traffic detection model to obtain the corresponding real-time abnormal traffic detection results.

[0173] The present invention discloses a business data protection method and system based on blockchain. By combining a blockchain network, an Hfish honeypot chain network, a data classification model, and an abnormal traffic detection model, it realizes the comprehensive protection of business data. Based on the cloud data center, it uniformly stores and manages the business center, reducing the hardware cost investment while improving the convenience of business data management and data value, and is more suitable for enterprise application scenarios with a large volume of business data. Utilizing the characteristics of blockchain such as decentralization and immutability, it ensures the authenticity and integrity of business data and improves the reliability of data storage. By creating an Hfish honeypot chain network to attract attackers, it protects the important data in the cloud data center from being attacked, improving the security of data storage and the protection level of the cloud data center. Combining encryption technology and digital identity technology further improves data security and prevents data leakage. By detecting abnormal traffic accessing the cloud data center and promptly discovering malicious attacks, it further improves data security.

[0174] The present invention is not limited to the above optional implementation manners, and anyone can obtain other various forms of products under the inspiration of the present invention. The above specific implementation manners should not be construed as limiting the protection scope of the present invention, and the protection scope of the present invention should be defined by the claims, and the specification can be used to interpret the claims.

Claims

1. A business data protection method based on blockchain, characterized in that: The steps include: Based on the cloud data center, a blockchain network, Hfish honeypot chain network, data classification model and abnormal traffic detection model are constructed, and keys are generated and identities are registered for all data collection devices connected to the cloud data center to obtain the public-private key pair and signature information of each data collection device; Based on the data collection device, and according to the private key and signature information in the public-private key pair, the collected real-time business data is encrypted and signed to obtain the corresponding encrypted real-time business data and real-time signature data, and upload them to the cloud data center; Based on the cloud data center, a trusted institution is called to perform signature verification on the real-time signature data. After the signature verification is passed, the encrypted real-time business data is decrypted according to the public key in the public-private key pair of the data acquisition device to obtain the corresponding decrypted real-time business data; The data confidentiality classification model is used to classify the decrypted real-time business data and obtain the corresponding real-time data confidentiality classification results. The decrypted real-time business data and the real-time data confidentiality classification results are stored on the blockchain network. The Hfish honeypot chain network is used to capture the real-time flow data of the data acquisition device. The abnormal flow detection model is used to perform abnormal flow detection on the real-time flow data to obtain the corresponding real-time abnormal flow detection results.

2. A blockchain-based business data protection method according to claim 1, characterized in that: Based on the cloud data center, a blockchain network, Hfish honeypot chain network, data classification model and abnormal traffic detection model are constructed, and keys are generated and identities are registered for all data acquisition devices connected to the cloud data center, and the public-private key pair and signature information of each data acquisition device are obtained, including the following steps: Based on the cloud data center, deploy management server nodes, smart contracts, IFPS systems and several data server nodes to build a blockchain network; Based on the blockchain network, the Hfish management module is deployed in the management server node, and the Hfish honeypot is deployed in each data server node to build the Hfish honeypot chain network; Based on some historical business data, a data classification model is constructed using a deep learning algorithm, and the data classification model is deployed to the management server node; Based on some historical traffic data, a deep learning algorithm is used to build an abnormal traffic detection model, and the abnormal traffic detection model is deployed in the Hfish management module; Collect attribute information and entity IDs of all data collection devices connected to the cloud data center, and send some attribute information and some entity IDs to a trusted institution; Based on the trusted institution, key generation and identity registration are performed on the data collection device according to the attribute information and entity ID, and the corresponding public-private key pair and signature information are obtained; The private key and signature information in the public-private key pair are sent to the corresponding data acquisition device, and the public key in the public-private key pair is published to the cloud data center.

3. A blockchain-based business data protection method according to claim 2, characterized in that: Based on the cloud data center, deploy management server nodes, smart contracts, IFPS system and several data server nodes to build a blockchain network, including the following steps: Based on the cloud data center, deploy several distributed connected data server nodes and collect network performance parameters of each data server node; According to network performance parameters and network requirements, a data server node with the best network performance is selected from a number of data server nodes as a management server node; Connect the management server node to the IFPS system, deploy smart contracts, and build a blockchain network.

4. A blockchain-based business data protection method according to claim 3, characterized in that: According to network performance parameters and network requirements, the IPCO algorithm is used to select the best data server node in the network from among several data server nodes as the management server node.

5. According to a blockchain-based business data protection method according to claim 2, it is characterized in that: The data classification model is constructed based on the N-GAN-MLP algorithm, where N is the total number of data classification dimensions.

6. A blockchain-based business data protection method according to claim 2, characterized in that: Based on the blockchain network, the Hfish management module is deployed in the management server node, and the Hfish honeypot is deployed in each data server node to build the Hfish honeypot chain network, including the following steps: Based on the blockchain network, the Hfish management module is deployed in the management server node according to the network performance parameters of the management server node; Generate corresponding Hfish honeypot elements according to the server system parameters of each data server node, and deploy Hfish honeypots in the data server nodes according to the Hfish honeypot elements; Set up a traffic probe in each Hfish honeypot and connect all traffic probes to the Hfish management module.

7. A blockchain-based business data protection method according to claim 6, characterized in that: Based on some historical traffic data, a deep learning algorithm is used to build an abnormal traffic detection model, and the abnormal traffic detection model is deployed in the Hfish management module, including the following steps: Collecting some historical traffic data, and preprocessing some historical traffic data to obtain some preprocessed historical traffic data; Based on some pre-processed historical traffic data, a deep learning algorithm is used to build an abnormal traffic detection model; The abnormal traffic detection model is deployed in the Hfish management module, and the input end of the abnormal traffic detection model is connected to all traffic probes.

8. A blockchain-based business data protection method according to claim 7, characterized in that: The abnormal traffic detection model is built based on the RF-BiLSTM algorithm.

9. A blockchain-based business data protection method according to claim 6, characterized in that: The data classification model is used to classify the decrypted real-time business data, and the corresponding real-time data classification results are obtained. The decrypted real-time business data and the real-time data classification results are stored on the blockchain network. The Hfish honeypot chain network is used to capture the real-time flow data of the data collection device, and the abnormal flow detection model is used to perform abnormal flow detection on the real-time flow data to obtain the corresponding real-time abnormal flow detection results, including the following steps: Based on the management server node of the blockchain network, the data confidentiality classification model is used to classify the decrypted real-time business data and obtain the corresponding real-time data confidentiality classification results; Based on the management server node, the decrypted real-time business data and the real-time data confidentiality classification results are stored, and the corresponding real-time business data hash value is generated; Call the smart contract to convert the real-time business data hash value into a real-time data block, generate the corresponding real-time data storage request, and send it to several data server nodes of the blockchain network; Based on several data server nodes, the PBFT consensus algorithm is used to reach a consensus on the intellectual property certification request. After the consensus is successful, the real-time data block is linked to the chain; Use the traffic probe of the Hfish honeypot in the Hfish honeypot chain network to capture the real-time traffic data of the data acquisition device and send it to the abnormal traffic detection model of the Hfish management module; Use the abnormal traffic detection model to perform abnormal traffic detection on real-time traffic data to obtain corresponding real-time abnormal traffic detection results; If the real-time abnormal traffic detection result shows that there is abnormal traffic, the corresponding data collection device is blocked by a firewall and added to the blacklist.

10. A blockchain-based business data protection system, used to implement the business data protection method according to any one of claims 1 to 9, characterized in that: The system includes a cloud data center, a trusted institution and several data acquisition devices, wherein the cloud data center and the trusted institution are respectively connected to the several data acquisition devices in communication, and the trusted institution is connected to the cloud data center in communication; The cloud data center includes an initialization unit, a data decryption unit, a data classification unit, an on-chain storage unit, and an abnormal traffic detection unit.

Images