A multi-dimensional linkage security encryption and decryption method for data based on privacy computing

Abstract

The present invention discloses a multi-dimensional linkage security encryption and decryption method for data based on privacy computing, which relates to the technical field of data security. The method includes Step 1: obtaining data and extracting the features and dimensions of the data; Step 2: splitting the data into several sub-data blocks according to the features and dimensions of the data; Step 3: encrypting each sub-data block through an encryption algorithm to generate several encrypted data blocks; Step 4: performing a correlation logic verification on the encrypted data of the encrypted data blocks to determine whether the encryption process of the encryption algorithm is correct; Step 5: performing a multi-dimensional linkage analysis on the encrypted data of the several encrypted data blocks through privacy computing to obtain multi-dimensional linkage analysis data; Step 6: decrypting the multi-dimensional linkage analysis data to obtain the final analysis result data. The present invention not only protects the privacy of the data but also can effectively judge the accuracy of the data, improving the security while also enhancing the user experience of the user.

Description

Technical Field

[0001] The present invention relates to the technical field of data security, and in particular to a multi-dimensional linkage security encryption and decryption method for data based on privacy computing. Background Art

[0002] In modern information society, data has become an important asset. With the rapid development of technologies such as big data, cloud computing, and artificial intelligence, multi-dimensional linkage analysis of data has become an important means to release data value. However, multi-dimensional linkage analysis of data often requires in-depth processing and analysis of data, which may involve data privacy and security issues.

[0003] Existing data security technologies usually adopt data desensitization and data encryption to protect data privacy and security. Data desensitization technology protects data privacy by fuzzifying data, making the data lose its original identity to a certain extent. Data encryption technology encrypts data through encryption algorithms, so that only authorized parties holding the correct key can decrypt and access the data. However, existing data desensitization technologies often affect the value of data, restricting the analysis and utilization of data. Secondly, although existing data encryption technologies can protect data privacy, they also increase the performance overhead of data processing and affect the efficiency of data processing. Moreover, due to the influence of encryption algorithms and processing performance, existing data encryption technologies may have encryption errors during the encryption process, resulting in incorrect results in multi-dimensional linkage analysis of data, and it is impossible to know whether the encryption process is correct in a timely manner due to the influence of data privacy protection, resulting in incorrect decrypted data output and affecting the user experience. Summary of the Invention

[0004] The object of the present invention is to overcome the disadvantages of existing data security technologies that require data desensitization processing, restricting the analysis and utilization of data, while data encryption technologies increase the performance overhead of data processing, affecting the efficiency of data processing, and having encryption errors during the encryption process, resulting in incorrect decryption of data and affecting the user experience. The present invention provides a multi-dimensional linkage security encryption and decryption method for data based on privacy computing. Through this method, data can have high data security without data desensitization processing, and at the same time, the data encryption process is verified to ensure the output of correct decrypted data.

[0005] The object of the present invention is achieved by the following technical solutions:

[0006] A multi-dimensional linkage security encryption and decryption method for data based on privacy computing, comprising the following steps:

[0007] Step 1, obtain data and preprocess the data, and then extract the features and dimensions of the data;

[0008] Step 2: Split the data into several sub - data blocks according to the characteristics and dimensions of the data, where each sub - data block represents a characteristic or a dimension;

[0009] Step 3: Encrypt each sub - data block through an encryption algorithm to generate several encrypted data blocks;

[0010] Step 4: Conduct a correlation logic verification on the encrypted data of the encrypted data blocks to determine whether the encryption process of the encryption algorithm is correct. If it is correct, jump to Step 5; if it is incorrect, adjust the parameters of the encryption algorithm and re - execute Step 3 until the encryption process of the encryption algorithm is correct;

[0011] Step 5: Conduct a multi - dimensional linkage analysis on the encrypted data of several encrypted data blocks through privacy computing to obtain multi - dimensional linkage analysis data;

[0012] Step 6: Decrypt the multi - dimensional linkage analysis data to obtain the final analysis result data.

[0013] In this solution, splitting the data into several sub - data blocks according to the characteristics and dimensions of the data is conducive to easier understanding and interpretation during data analysis, facilitates subsequent multi - dimensional linkage analysis, and reduces the overall computational complexity. Conducting a multi - dimensional linkage analysis on the encrypted data of several encrypted data blocks through privacy computing ensures that during the data analysis and processing process, the data always exists in ciphertext form. Even if an attacker cracks the privacy computing method, the data obtained by restoring the multi - dimensional linkage analysis data is only encrypted data. This solution effectively protects the confidentiality and integrity of the data, so there is no need to perform data desensitization to protect data privacy. At the same time, since this solution first encrypts each sub - data block and then conducts a multi - dimensional linkage analysis on the encrypted data, it is also necessary to determine whether the encryption process of the encryption algorithm is correct to ensure that the data obtained after decrypting the multi - dimensional linkage analysis is true and valid. Although the data after passing through the encryption algorithm is encrypted, it is still derived from the original data conversion, so there is still a logical correlation between the encrypted data. Therefore, this solution conducts a correlation logic verification on the encrypted data to determine whether the encryption process of the encryption algorithm is correct, which can avoid the situation where an error in the encryption algorithm leads to an incorrect result when decrypting the multi - dimensional linkage analysis data. Since the data is still encrypted during the correlation logic verification process, the verification process will not disclose the real data, achieving both the protection of data privacy and the judgment of data accuracy.

[0014] Preferably, in Step 4, when conducting a correlation logic verification on the encrypted data of the encrypted data blocks to determine whether the encryption process of the encryption algorithm is correct, specifically:

[0015] Obtain the correlation characteristics of the encrypted data of at least two encrypted data blocks, where the correlation characteristics include positive correlation, negative correlation, and mutual exclusivity;

[0016] For positively correlated encrypted data blocks, determine whether their correlation coefficient is greater than or equal to the set positive correlation threshold. If it is greater than or equal to the set positive correlation threshold, then determine that these encrypted data blocks are positively correlated and the encryption process of the encryption algorithm is correct. If it is less than the set positive correlation threshold, then determine that there is no correlation between these encrypted data blocks and the encryption process of the encryption algorithm is incorrect;

[0017] For negatively correlated encrypted data blocks, determine whether their correlation coefficient is less than or equal to the set negative correlation threshold. If it is less than or equal to the set negative correlation threshold, then determine that these encrypted data blocks are negatively correlated and the encryption process of the encryption algorithm is correct. If it is greater than the set positive correlation threshold, then determine that there is no correlation between these encrypted data blocks and the encryption process of the encryption algorithm is incorrect;

[0018] For mutually exclusive encrypted data blocks, determine whether the sum of the values of the encrypted data of the mutually exclusive encrypted data blocks is within the set mutual exclusion threshold range. If it is within the mutual exclusion threshold range, then determine that there is mutual exclusivity between these encrypted data and the encryption process of the encryption algorithm is correct. Otherwise, determine that there is no correlation between these encrypted data and the encryption process of the encryption algorithm is incorrect.

[0019] Data in different dimensions must have an association relationship. The design of this solution takes into account positive correlation, negative correlation, and mutual exclusivity. Although the data is encrypted, there is still a correlation between data in different dimensions. Therefore, this solution uses positive correlation, negative correlation, and mutual exclusivity to determine whether the encryption process of the encryption algorithm is correct. If there is an association between multiple encrypted data blocks, the number of encrypted data blocks selected for association logic verification will be flexibly selected according to actual needs. If the number of encrypted data blocks is small, the accuracy of logic verification may also decrease accordingly. If the number of encrypted data blocks is large, the computational amount will also increase accordingly.

[0020] Preferably, in step 1, the data is preprocessed, specifically:

[0021] Obtain the sensitive items of the data, and perform anonymization and de-identification processing on the sensitive item data. The anonymization and de-identification processing include data perturbation, pseudonymization, generalization, and data suppression. The design of this solution prevents the identity of individuals or entities from being identified and further protects the privacy and security of the data.

[0022] Preferably, in step 2, the sub-data blocks are also randomized. The randomization processing includes randomly rearranging, permuting, or adding noise to the data, and partially or fully using random perturbation for the data within the sub-data blocks.

[0023] Preferably, step 3 is specifically as follows:

[0024] Use a lightweight symmetric encryption algorithm to encrypt the data of the sub-data block to generate encrypted data;

[0025] Store the encrypted data in a local storage device, cloud storage, or distributed storage system, and the stored encrypted data constitutes an encrypted data block.

[0026] Preferably, in step 5, multi-dimensional linkage analysis is performed on the encrypted data of several encrypted data blocks through privacy computing, including:

[0027] Use homomorphic encryption technology to perform arithmetic operations on the encrypted data, and the arithmetic operations include addition and multiplication;

[0028] For multiple encrypted data blocks, perform homomorphic encryption separately through multi-party secure computing, and then merge the data encrypted by each party to obtain multi-dimensional linkage analysis data.

[0029] Preferably, after obtaining the final analysis result data, sharing and exchange control are also performed on the analysis result data, specifically as follows:

[0030] The owner of the analysis result data encrypts the analysis result data and publishes it to the data sharing platform, sets an access control policy, and defines a set of user attributes allowed to access the data;

[0031] The data requester sends an access request to the data sharing platform and provides its own attribute proof;

[0032] The data sharing platform verifies whether the user's attributes meet the access control policy set by the data owner based on the attribute-based encryption method, and is allowed to access the data after meeting the access control policy;

[0033] The data sharing platform provides the key required for decryption or directly decrypts the analysis result data, and the data requester obtains the decrypted analysis result data.

[0034] Preferably, the attribute-based encryption method is specifically the ciphertext-policy attribute-based encryption method. When encrypting the data, the owner of the analysis result data embeds an access control policy, and only users whose set of attributes meets the access policy are allowed to access the data. The design of this solution enhances the flexibility and security of data access control, and supports complex permission management and fine-grained access control.

[0035] Preferably, the multi-dimensional linkage security encryption and decryption method based on privacy computing also performs fine-grained control and obfuscation processing on the analysis result data. The design of this solution ensures that users can only obtain the data information within their authority range, preventing excessive exposure of data.

[0036] Preferably, in step 6, after decrypting the multi-dimensional linkage analysis data, noise or perturbation is added to the encryption result according to the differential privacy algorithm. The design of this solution can prevent attackers from reverse-inferring the original data through the analysis results, improve the security and privacy protection level of data analysis, and at the same time ensure the effectiveness and accuracy of the analysis results.

[0037] The beneficial effects of the present invention are as follows: By performing correlation logic verification on the encrypted data to determine whether the data in the confidential algorithm confidential process is correct, it is possible to avoid the situation where errors in the multi-dimensional linkage analysis of encrypted data lead to incorrect decryption results of the multi-dimensional linkage analysis data, ensuring the accuracy of the multi-dimensional linkage analysis results. Since the data is still encrypted during the correlation logic verification, the verification process will not disclose the real data, achieving both protection of data privacy and determination of data accuracy.

[0038] The present invention effectively protects the confidentiality and integrity of data, so there is no need to perform data desensitization to protect data privacy. The lightweight symmetric encryption algorithm used in the present invention can reduce the performance overhead during the encryption process and improve the efficiency of data processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is a flowchart of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0040] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more complete and will fully convey the concept of the example embodiments to those skilled in the art.

[0041] In addition, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present application. However, those skilled in the art will realize that the technical solutions of the present application can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. can be used. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the present application.

[0042] The flowchart shown in the drawings is only an exemplary illustration and does not necessarily include all the contents and operations / steps, nor is it necessary to be executed in the described order. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to the actual situation.

[0043] Example 1: A multi-dimensional linked security encryption and decryption method for data based on privacy computing, as Figure 1 shown, includes the following steps:

[0044] Step 1: Obtain the data and preprocess the data, then extract the features and dimensions of the data;

[0045] Step 2: Divide the data into several sub-data blocks according to the features and dimensions of the data, and each sub-data block represents a feature or a dimension;

[0046] Step 3: Encrypt each sub-data block through an encryption algorithm to generate several encrypted data blocks;

[0047] Step 4: Conduct multi-dimensional linked analysis on the encrypted data of several encrypted data blocks through privacy computing to obtain multi-dimensional linked analysis data;

[0048] Step 5: Conduct relevance logic verification on the multi-dimensional linked analysis data to determine whether the multi-dimensional linked analysis data is correct. If it is correct, jump to Step 6. If it is incorrect, adjust the parameters of the multi-dimensional linked analysis and re-execute Step 4 until the multi-dimensional linked analysis data is correct;

[0049] Step 6: Decrypt the multi-dimensional linked analysis data to obtain the final analysis result data.

[0050] In this solution, the data is segmented into several sub-data blocks according to the characteristics and dimensions of the data, which is conducive to easier understanding and interpretation during data analysis, facilitates subsequent multi-dimensional linkage analysis, and reduces the complexity of overall calculation. Through privacy computing, multi-dimensional linkage analysis is performed on the encrypted data of several encrypted data blocks, ensuring that the data always exists in ciphertext form during data analysis and processing. Even if an attacker cracks the privacy computing method, the data obtained by restoring the multi-dimensional linkage analysis data is only encrypted data. This solution effectively protects the confidentiality and integrity of the data, so there is no need to perform data desensitization to protect data privacy. At the same time, since this solution first encrypts each sub-data block and then performs multi-dimensional linkage analysis on the encrypted data, it is also necessary to judge whether the encryption process of the encryption algorithm is correct to ensure that the data decrypted after multi-dimensional linkage analysis is true and valid. Although the data after passing through the encryption algorithm is encrypted, it is still obtained by converting the original data. Therefore, there is still a logical correlation between the encrypted data. Therefore, this solution verifies the correlation logic of the encrypted data to judge whether the encryption process of the encryption algorithm is correct, and can prevent the situation where an error in the encryption algorithm leads to an incorrect result of decrypting the multi-dimensional linkage analysis data. Since the data is still encrypted during the correlation logic verification, the verification process will not disclose the real data, achieving both the protection of data privacy and the judgment of data accuracy.

[0051] In step 4 described above, the correlation logic of the encrypted data of the encrypted data block is verified to judge whether the encryption process of the encryption algorithm is correct. Specifically:

[0052] Obtain the correlation characteristics of the encrypted data of at least two encrypted data blocks. The correlation characteristics include positive correlation, negative correlation, and mutual exclusion;

[0053] For the positively correlated encrypted data blocks, judge whether their correlation coefficient is greater than or equal to the set positive correlation threshold. If it is greater than or equal to the set positive correlation threshold, judge that these encrypted data blocks are positively correlated and the encryption process of the encryption algorithm is correct. If it is less than the set positive correlation threshold, judge that there is no correlation between these encrypted data blocks and the encryption process of the encryption algorithm is incorrect;

[0054] For the negatively correlated encrypted data blocks, judge whether their correlation coefficient is less than or equal to the set negative correlation threshold. If it is less than or equal to the set negative correlation threshold, judge that these encrypted data blocks are negatively correlated and the encryption process of the encryption algorithm is correct. If it is greater than the set positive correlation threshold, judge that there is no correlation between these encrypted data blocks and the encryption process of the encryption algorithm is incorrect;

[0055] For mutually exclusive encrypted data blocks, it is determined whether the sum of the values of the encrypted data in the mutually exclusive encrypted data blocks is within the set mutual exclusion threshold range. If it is within the mutual exclusion threshold range, it is determined that there is mutual exclusion among these encrypted data and the encryption process of the encryption algorithm is correct; otherwise, it is determined that there is no correlation among these encrypted data and the encryption process of the encryption algorithm is incorrect.

[0056] Data in different dimensions must have an association relationship. The design of this solution takes into account positive correlation, negative correlation, and mutual exclusion. Although the multi-dimensional linkage data is encrypted, there is still a correlation between data in different dimensions. Therefore, this solution uses positive correlation, negative correlation, and mutual exclusion to determine whether the multi-dimensional linkage analysis data is correct. If there is an association among multiple encrypted data blocks, the number of encrypted data blocks selected for association logic verification will be flexibly selected according to actual needs. If the number of encrypted data blocks is small, the accuracy of logic verification may decrease accordingly; if the number of encrypted data blocks is large, the calculation amount will also increase accordingly.

[0057] In this embodiment, for positively correlated encrypted data blocks, the Pearson correlation coefficient is used to measure the correlation between them. Suppose there are two encrypted data blocks A and B, each containing n encrypted data points, denoted as A1, A2,..., An and B1, B2,..., Bn respectively. The calculation formula for the Pearson correlation coefficient is as follows:

[0058] ;

[0059] Among them, represents the correlation coefficient, and represent the means of encrypted data block A and encrypted data block B respectively, and represent the value of a certain item in encrypted data block A and encrypted data block B respectively.

[0060] For negatively correlated encrypted data blocks, the Pearson correlation coefficient is also used for judgment, only the threshold range setting for the correlation coefficient is different.

[0061] Suppose there are three encrypted data blocks A, B, and C, and verify the correlation between them:

[0062] The correlation coefficient r between A and B is calculated as 0.8, and the set positive correlation threshold is 0.7. Therefore, A and B are positively correlated, and the encryption process of the encryption algorithm is correct. The correlation coefficient r between A and C is calculated as -0.9, and the set negative correlation threshold is -0.7. Therefore, A and C are negatively correlated, and the encryption process of the encryption algorithm is correct. The cumulative sum S of B and C is calculated as 0.5, and the set exclusive threshold range is [0, 1]. Therefore, B and C are mutually exclusive, and the encryption process of the encryption algorithm is correct.

[0063] In step 1 described above, the data is preprocessed, specifically:

[0064] The original data is cleaned, normalized, dimensionally reduced, and format-converted to ensure the quality, consistency, and usability of the data, eliminate noise, missing values, and outliers, and lay a foundation for subsequent data analysis. The sensitive items of the data are obtained, and the sensitive item data is anonymized and de-identified. The anonymization and de-identification processes include data perturbation, pseudonymization, generalization, and data suppression. The design of this solution prevents the identity of individuals or entities from being identified and further protects the privacy and security of the data.

[0065] In step 2 described above, the sub-data blocks are also randomized. The randomization process includes randomly rearranging, permuting, or adding noise to the data, and partially or fully using random perturbation on the data within the sub-data blocks.

[0066] Step 3 is specifically:

[0067] A lightweight symmetric encryption algorithm is used to encrypt the data of the sub-data blocks to generate encrypted data;

[0068] The encrypted data is stored in a local storage device, cloud storage, or distributed storage system, and the stored encrypted data constitutes an encrypted data block.

[0069] In this embodiment, the lightweight symmetric encryption algorithm can be an improved AES algorithm or a lightweight block cipher algorithm, which can reduce the performance overhead during the encryption process and improve the efficiency of data processing.

[0070] In step 4 described above, multi-dimensional linkage analysis is performed on the encrypted data of several encrypted data blocks through privacy computing, including:

[0071] Using homomorphic encryption technology to perform arithmetic operations on the encrypted data. The arithmetic operations include addition and multiplication;

[0072] For multiple encrypted data blocks, homomorphic encryption is separately performed using multi-party secure computing, and then the homomorphically encrypted data of each party is merged to obtain multi-dimensional linkage analysis data.

[0073] After obtaining the final analysis result data, sharing and exchange control are also performed on the analysis result data, specifically as follows:

[0074] The owner of the analysis result data encrypts the analysis result data and publishes it to the data sharing platform, sets an access control policy, and defines a set of user attributes allowed to access the data;

[0075] The data requester sends an access request to the data sharing platform and provides its own attribute proof;

[0076] The data sharing platform verifies whether the user's attributes meet the access control policy set by the data owner based on the attribute-based encryption method. After meeting the access control policy, the user is allowed to access the data;

[0077] The data sharing platform provides the key required for decryption or directly decrypts the analysis result data, and the data requester obtains the decrypted analysis result data.

[0078] The specific attribute-based encryption method is to adopt the ciphertext-policy attribute-based encryption method. When encrypting the data, the owner of the analysis result data embeds the access control policy, and only users whose attribute set meets the access policy are allowed to access the data. The design of this solution enhances the flexibility and security of data access control, and supports complex permission management and fine-grained access control.

[0079] The multi-dimensional linkage security encryption and decryption method based on privacy computing also performs fine-grained control and obfuscation processing on the analysis result data. The design of this solution ensures that users can only obtain the data information within their authority, preventing excessive exposure of data.

[0080] In step 6 described above, after decrypting the multi-dimensional linkage analysis data, noise or perturbation is added to the encryption result according to the differential privacy algorithm. The design of this solution can prevent attackers from reverse-inferring the original data through the analysis result, improve the security and privacy protection level of data analysis, and at the same time ensure the effectiveness and accuracy of the analysis result.

[0081] During the data encryption process, parallel encryption technology and hardware acceleration means such as GPU acceleration, FPGA acceleration or dedicated encryption chips are used to perform parallel encryption processing on multiple sub-data blocks, significantly improving the efficiency of data encryption, reducing the performance overhead of data processing, and meeting the real-time requirements.

[0082] The following is a specific application of obtaining the enterprise carbon emission result based on the historical energy consumption data of the enterprise through the method of this embodiment:

[0083] Obtain the historical energy consumption data of the enterprise. These data should include the energy consumption records of different enterprises, such as the consumption amounts of energy sources such as coal, oil, and gas, as well as the consumption timestamps;

[0084] According to the characteristics and dimensions of the data, the data is segmented into several sub-data blocks. For example, the data is segmented according to dimensions such as energy type (coal, oil, gas, clean energy, etc.) and time period (year, month, day), and each sub-data block is encrypted. At the same time, a correlation logic verification is performed on the encrypted data. For example, there is a negative correlation between clean energy and fossil energy, and a positive correlation between energy consumption and carbon emission factors, etc.

[0085] Perform multi-dimensional linkage analysis on the encrypted data blocks through privacy computing technology. Merge the encrypted results calculated by all parties to obtain the final carbon emission result data.

[0086] Decrypt the encrypted carbon emission results obtained from the multi-dimensional linkage analysis. Use the corresponding decryption key and lightweight decryption algorithm to restore the original carbon emission result data.

[0087] Enterprises can use the decrypted carbon emission result data for decision support, business optimization, etc. For example, formulate emission reduction plans according to carbon emissions, optimize the energy use structure, etc.

[0088] Embodiment 2: A multi-dimensional linkage security encryption and decryption method for data based on privacy computing. Its principle and implementation method are basically the same as those of Embodiment 1. The difference lies in that in the specific implementation method of performing a correlation logic verification on the encrypted data of the encrypted data block to determine whether the encryption process of the encryption algorithm is correct, the minimum value, maximum value, quartiles, and standard deviation of the data encrypted data block are also obtained and calculated:

[0089] For positively correlated encrypted data blocks and negatively correlated encrypted data blocks, determine whether the minimum value, maximum value, quartiles, and standard deviation of the encrypted data block are within a reasonable range. For mutually exclusive encrypted data blocks, check whether the minimum value and the maximum value are complementary, and determine whether there is an overlapping area between the two mutually exclusive encrypted data blocks through quartiles and standard deviation.

[0090] After considering the specification and the disclosed embodiments herein, those skilled in the art will readily conceive of other embodiments of the present application. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include the common general knowledge or conventional technical means in the technical field not disclosed in the present application.

[0091] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A data multi-dimensional linkage security encryption and decryption method based on privacy computing, characterized in that: The following steps are involved: Step 1: Obtain and preprocess the data, and then extract the features and dimensions of the data; Step 2: divide the data into several sub-data blocks according to the characteristics and dimensions of the data, each sub-data block represents a feature or a dimension; Step 3, encrypting each sub-data block by an encryption algorithm to generate a number of encrypted data blocks; Step 4, obtaining correlation characteristics of the encrypted data of at least two encrypted data blocks, the correlation characteristics include positive correlation, negative correlation and mutual exclusivity, performing correlation logic verification on the encrypted data of the encrypted data blocks, and judging whether the encryption process of the encryption algorithm is correct. If it is correct, jump to step 5; if it is not correct, adjust the parameters of the encryption algorithm and re-execute step 3 until the encryption process of the encryption algorithm is correct; Step 5: Perform multi-dimensional linkage analysis on the encrypted data of several encrypted data blocks through privacy computing to obtain multi-dimensional linkage analysis data; Step 6: Decrypt the multi-dimensional linkage analysis data to obtain the final analysis result data.

2. According to the method of claim 1, the method is characterized in that: In step 4, the encrypted data of the encrypted data block is subjected to correlation logic verification to determine whether the encryption algorithm encryption process is correct, specifically: Obtaining correlation characteristics of encrypted data of at least two encrypted data blocks, the correlation characteristics including positive correlation, negative correlation and mutual exclusivity; For positively correlated encrypted data blocks, determine whether their correlation coefficients are greater than or equal to a set positive correlation threshold. If they are greater than or equal to the set positive correlation threshold, then it is determined that these encrypted data blocks are positively correlated and the encryption process of the encryption algorithm is correct. If they are less than the set positive correlation threshold, then it is determined that these encrypted data blocks are not correlated and the encryption process of the encryption algorithm is wrong. For the negatively correlated encrypted data blocks, determine whether their correlation coefficient is less than or equal to the set negative correlation threshold. If it is less than or equal to the set negative correlation threshold, then it is determined that these encrypted data blocks are negatively correlated and the encryption process of the encryption algorithm is correct. If it is greater than the set positive correlation threshold, then it is determined that these encrypted data blocks do not have correlation and the encryption process of the encryption algorithm is wrong. For mutually exclusive encrypted data blocks, determine whether the values ​​of the encrypted data of the mutually exclusive encrypted data blocks are within the set mutual exclusion threshold range after cumulative calculation. If they are within the mutual exclusion threshold range, it is determined that these encrypted data are mutually exclusive and the encryption process of the encryption algorithm is correct. Otherwise, it is determined that there is no correlation between these encrypted data and the encryption process of the encryption algorithm is wrong.

3. According to the method of claim 1, the method is characterized in that: In step 1, the data is preprocessed, specifically: Acquire sensitive items of the data and perform anonymization and de-identification processing on the sensitive item data. The anonymization and de-identification processing includes data perturbation, pseudonymization, generalization and data suppression.

4. According to the method of claim 1, the method is characterized in that: In the step 2, the sub-data blocks are also subjected to random processing, and the random processing includes randomly rearranging, replacing or adding noise to the data, and randomly perturbing part or all of the data in the sub-data blocks.

5. According to the method of claim 1, the method is characterized in that: The step 3 is specifically as follows: A lightweight symmetric encryption algorithm is used to encrypt the data of the sub-data block to generate encrypted data; The encrypted data is stored in a local storage device, cloud storage, or distributed storage system, and the stored encrypted data constitutes an encrypted data block.

6. According to the method of claim 1, the method is characterized in that: In step 5, a multi-dimensional linkage analysis is performed on the encrypted data of several encrypted data blocks through privacy computing, including: Use homomorphic encryption technology to perform arithmetic operations on encrypted data, including addition and multiplication; Multi-party secure computing is used to perform homomorphic encryption on multiple encrypted data blocks separately, and then the data homomorphically encrypted by all parties are merged to obtain multi-dimensional linkage analysis data.

7. According to the method of claim 1, the method is characterized in that: After obtaining the final analysis result data, the analysis result data is also shared and exchanged, specifically: The owner of the analysis result data encrypts the analysis result data and publishes it to the data sharing platform, sets the access control policy, and defines the user attribute set that is allowed to access the data; The data requester sends an access request to the data sharing platform and provides its own attribute proof; The data sharing platform verifies whether the user's attributes meet the access control policy set by the data owner based on the attribute-based encryption method. If the user meets the access control policy, he / she is allowed to access the data. The data sharing platform provides the key required for decryption or directly decrypts the analysis result data, and the data requester obtains the decrypted analysis result data.

8. According to the method of claim 7, the multi-dimensional linkage data security encryption and decryption method based on privacy computing is characterized in that: The attribute-based encryption method specifically adopts a ciphertext strategy attribute-based encryption method. The owner of the analysis result data embeds an access control policy when encrypting the data. Only users whose attribute sets meet the access policy are allowed to access the data.

9. A data multi-dimensional linkage security encryption and decryption method based on privacy computing according to claim 7 or 8, characterized in that: The analysis result data is also subjected to fine-grained control and fuzzy processing.

10. According to the method of claim 1, the method is characterized in that: In step 6, after the multi-dimensional linkage analysis data is decrypted, noise or disturbance is added to the encryption result according to the differential privacy algorithm.

Images