Privacy protection strengthening method and system in data processing service

Abstract

The invention discloses a privacy protection strengthening method and system in a data processing service, and the method comprises the following steps: obtaining to-be-processed service data, building a block chain network architecture through an alliance chain or a public chain according to the to-be-processed service data, verifying the data in a block chain, and carrying out the verification of the data in the block chain. Executing data privacy protection according to the smart contract, dynamically controlling data access authority, and recording all data operation logs; the method comprises the following steps: realizing federated learning on a plurality of distributed nodes, constructing privacy protection data sharing, reserving local data on each node, adding uploaded model parameter noise in a differential privacy mode, constructing a federated learning model, and allowing node proving calculation to be legal through a zero-knowledge proving mechanism; encryption protection is performed in the whole process from data storage, processing to transmission, and the possible privacy leakage risk in a traditional method is avoided. The smart contract is combined with the block chain, so that the compliance of the data processing process can be automatically detected and ensured in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing services, and in particular to a method and system for enhancing privacy protection in data processing services. Background Art

[0002] With the rapid development of information technology, data processing services have been widely used in various fields. Whether it is Internet companies, financial institutions, healthcare industries or government departments, they all rely on large amounts of data processing to support decision-making, provide services and tap value. For example, Internet companies achieve precision marketing by analyzing users' browsing history, purchasing behavior and social interaction data; financial institutions rely on customers' transaction data to assess risks and provide personalized financial products; and the healthcare industry processes large amounts of patient medical records data for disease diagnosis and research.

[0003] Traditional privacy protection methods, such as data encryption, are vulnerable to technological breakthroughs, especially when data is stored in central servers, which can easily expose the original data.

[0004] When transferring data across borders, it is difficult to ensure data privacy protection while complying with the laws and regulations of various countries (such as GDPR and CCPA).

[0005] Although homomorphic encryption can ensure data privacy, its computational complexity is high and affects system performance.

[0006] The lack of transparency in each link of data processing can easily lead to trust issues.

[0007] Traditional privacy protection inventions lack effective means to precisely control data access and usage rights.

[0008] Based on these issues, we propose a method and system for enhancing privacy protection in data processing services. Summary of the invention

[0009] In order to solve one of the above technical problems, a privacy protection enhancement method and system in data processing services is provided, which utilizes a variety of cutting-edge technologies such as blockchain, homomorphic encryption, zero-knowledge proof, and federated learning, and proposes solutions to bottlenecks such as privacy leakage, compliance issues, computing efficiency, and data security in existing technologies. Through multi-level privacy protection mechanisms, smart contract automated compliance checks, efficient privacy computing frameworks, and cross-border data flow compliance processing, data privacy protection is ensured, and significant progress has been made in computing efficiency, transparency, and compliance, solving the problem.

[0010] In order to achieve the above objectives, the technical inventions adopted by the present invention are:

[0011] A first aspect: A method for enhancing privacy protection in a data processing service, comprising the following steps:

[0012] Obtain the service data to be processed, build a blockchain network architecture through a consortium chain or a public chain based on the service data to be processed, verify the data in the blockchain, perform data privacy protection and dynamically control data access rights according to smart contracts, and record all data operation logs. The consortium chain or public chain includes Ethereum or Hyper ledger;

[0013] The data privacy protection is implemented according to the smart contract and the data access rights are dynamically controlled. The execution process formula is as follows:

[0014] Execute Transaction(Data, Access Permissions, Compliance Rules);

[0015] in:

[0016] Data is data;

[0017] Access Permissions is access rights;

[0018] Compliance Rules are compliance rules;

[0019] Based on the implementation of federated learning on multiple distributed nodes, privacy-preserving data sharing is constructed. Each node retains local data, and noise is added to the uploaded model parameters through differential privacy. A federated learning model is constructed, and the zero-knowledge proof mechanism allows nodes to prove the legality of the calculation, including:

[0020] Federated learning is performed on multiple distributed nodes, where each node only accesses and processes local data and aggregates the locally trained model parameters by periodically uploading them to a central server.

[0021] Each time a local model update is uploaded, noise is added to the uploaded model parameters based on differential privacy.

[0022] Based on zero-knowledge proof, the model update submitted by each node is verified to be compliant. The model update formula is:

[0023]

[0024] in, is the model after training the i-th node, D i is the local data of the i-th node, θ i is the initial parameter for training;

[0025] Data is encrypted using homomorphic encryption technology. All computing tasks are performed in an encrypted state, and the computing results are encrypted data until they are decrypted by authorized users. Specifically, they include:

[0026] Homomorphic encryption technology allows calculations to be performed on encrypted data, and the calculation results remain encrypted. User data is encrypted and uploaded to a central server, which performs encrypted calculations. Homomorphic encryption technology includes partial homomorphic encryption and full homomorphic encryption.

[0027] Optimize the performance loss after homomorphic encryption, accelerate encryption calculations through hardware acceleration, and use parallel computing to distribute tasks to multiple nodes for processing;

[0028] User data is uploaded in encrypted form, and the central server performs encrypted calculations. The calculation results remain in encrypted form until the authorized user decrypts them;

[0029] Automated compliance audits are performed based on smart contracts. The compliance rules will be embedded in smart contracts to automatically check whether data processing behavior is legal. Based on the blockchain network architecture and smart contracts and in response to regionalized compliance controls on cross-border data flows, it is determined that data complies with compliance requirements when flowing across borders, including:

[0030] Automatically audit the data processing process based on smart contracts. All data processing rules and privacy policies are embedded in smart contracts to automatically verify data access and processing behaviors.

[0031] Compliance controls in response to cross-border data flows through smart contracts;

[0032] The encryption strategy and storage location of data during flow are automatically adjusted by smart contracts;

[0033] Based on the blockchain network architecture and smart contracts, fine-grained control of data access is achieved. Authorized users are allowed to access data through blockchain verification. The blockchain records all access behaviors and finally strengthens privacy protection, including:

[0034] Fine-grained permission management based on blockchain network architecture. Users can only access authorized data. All access requests are verified through blockchain, and user permissions are dynamically adjusted according to different data types and roles.

[0035] Audit and permission behavior records, all user permission changes and data access logs are saved in the blockchain.

[0036] Use consortium chains or public chains (such as Ethereum or Hyperledger) to build a transparent management system to ensure that all data processing activities, privacy protection measures, and compliance audits are recorded on the blockchain.

[0037] The data in the blockchain cannot be tampered with. All data uploading, processing, querying and other behaviors must be verified by the blockchain to ensure the transparency and non-tamperability of the data processing process.

[0038] Use smart contracts to automatically execute privacy protection policies, dynamically control data access permissions, and record all data operation logs.

[0039] The blockchain records all access and processing behaviors on the chain, achieving real-time auditable access control, ensuring that all operations are traceable, and solving transparency issues.

[0040] A second aspect: A privacy protection enhancement system in a data processing service, comprising:

[0041] The data acquisition module is used to obtain the service data to be processed, build a blockchain network architecture through a consortium chain or a public chain based on the service data to be processed, verify the data in the blockchain, perform data privacy protection and dynamically control data access rights based on smart contracts, and record all data operation logs;

[0042] The privacy-preserving data sharing module is used to implement federated learning on multiple distributed nodes and build privacy-preserving data sharing. Each node retains local data and adds noise to the uploaded model parameters through differential privacy to build a federated learning model. The zero-knowledge proof mechanism allows nodes to prove the legality of the calculation.

[0043] The calculation encryption data module is used to encrypt data according to homomorphic encryption technology. All calculation tasks are performed in an encrypted state, and the calculation results are encrypted data until they are decrypted by authorized users.

[0044] A compliance rules audit module is used to perform automated compliance rules audits based on smart contracts. The compliance rules will be embedded in smart contracts to automatically check whether data processing behaviors are legal. Based on the blockchain network architecture and smart contracts and in response to regionalized compliance controls on cross-border data flows, it is determined that data complies with compliance requirements when flowing across borders.

[0045] The fine-grained permission management and audit module is used to implement fine-grained control of data access based on the blockchain network architecture and smart contracts. Authorized users are allowed to access data through blockchain verification. The blockchain records all access behaviors and finally strengthens privacy protection.

[0046] A third aspect: A computer device comprising:

[0047] processor;

[0048] A memory for storing executable instructions;

[0049] The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the privacy protection enhancement method in the data processing service.

[0050] A fourth aspect: A computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor implements the privacy protection enhancement method in the data processing service.

[0051] Compared with the prior art, the present invention has the following beneficial effects:

[0052] 1. From data storage, processing to transmission, the entire process is encrypted and protected, avoiding the possible privacy leakage risks in traditional inventions.

[0053] 2. The combination of smart contracts and blockchain can automatically detect and ensure the compliance of data processing in real time.

[0054] 3. The combination of federated learning and homomorphic encryption optimizes the performance of privacy computing and realizes a decentralized data sharing mechanism.

[0055] 4. In response to the issue of cross-border data flow, an automatic compliance mechanism is proposed to effectively meet the requirements of privacy protection.

[0056] 5. The present invention can not only improve the privacy protection capabilities of data processing services, but also achieve a more efficient, transparent and compliant data management model, providing more reliable technical support for enterprises and individuals in data privacy protection and compliance. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A flowchart of a method for enhancing privacy protection in a data processing service of the present invention;

[0058] Figure 2 This is a module diagram of the privacy protection enhancement system in the data processing service of the present invention.

[0059] Figure 3 It is a schematic diagram of the structure of the computer device of the present invention;

[0060] In the figure, 10 is a computer device; 1002 is a processor; 1004 is a memory; and 1006 is a transmission device. DETAILED DESCRIPTION

[0061] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0062] Embodiment 1:

[0063] Traditional privacy protection methods, such as data encryption, are vulnerable to technological breakthroughs, especially when data is stored in central servers, which can easily expose the original data.

[0064] When transferring data across borders, it is difficult to ensure data privacy protection while complying with the laws and regulations of various countries (such as GDPR and CCPA).

[0065] Although homomorphic encryption can ensure data privacy, its computational complexity is high and affects system performance.

[0066] The lack of transparency in each link of data processing can easily lead to trust issues.

[0067] Traditional privacy protection solutions lack effective means to precisely control data access and usage rights.

[0068] Reference Figure 1 As shown, a privacy protection enhancement method in a data processing service includes the following steps:

[0069] Step 10: Obtain the service data to be processed, build a blockchain network architecture through a consortium chain or a public chain according to the service data to be processed, verify the data in the blockchain, perform data privacy protection and dynamically control data access rights according to the smart contract, and record all data operation logs. The consortium chain or the public chain includes Ethereum or Hyper ledger.

[0070] The data privacy protection is implemented according to the smart contract and the data access rights are dynamically controlled. The execution process formula is as follows:

[0071] Execute Transaction(Data, Access Permissions, Compliance Rules);

[0072] in:

[0073] Data is data;

[0074] Access Permissions is access rights;

[0075] Compliance Rules are compliance rules;

[0076] Step 20: Based on the implementation of federated learning on multiple distributed nodes, privacy-preserving data sharing is constructed. Each node retains local data, and noise is added to the uploaded model parameters through differential privacy. A federated learning model is constructed, and the zero-knowledge proof mechanism allows nodes to prove the legality of the calculation, including:

[0077] Federated learning on multiple distributed nodes, where each node only accesses and processes local data and aggregates the locally trained model parameters by periodically uploading them to the central server;

[0078] Each time a local model update is uploaded, noise is added to the uploaded model parameters based on differential privacy.

[0079] Based on zero-knowledge proof, the model update submitted by each node is verified to be compliant. The model update formula is:

[0080]

[0081] in, is the model after training the i-th node, D i is the local data of the i-th node, θ i is the initial parameter for training;

[0082] Federated learning is implemented on multiple distributed nodes. Each node can only access and process local data. The data will not leave the local node, ensuring data privacy.

[0083] By regularly uploading locally trained model parameters (such as gradients) to the central server for aggregation, the original data is not transmitted;

[0084] Each time a local model update (such as gradient) is uploaded, differential privacy technology is used to add noise to the uploaded model parameters to ensure that the user's private information cannot be inferred from it.

[0085] Differential privacy formula:

[0086]

[0087] in, is the model after adding noise, Indicates that the mean is 0 and the variance is σ 2 Gaussian noise;

[0088] Use zero-knowledge proof (ZKP) to verify the compliance of model updates submitted by each node without revealing any training data or gradient content.

[0089] Zero-knowledge proof verification formula:

[0090]

[0091] in, The model update submitted for node i, It is a verification of the legitimacy of the model update.

[0092] Step 30: Encrypt the data using homomorphic encryption technology. All computing tasks are performed in an encrypted state. The computing results are encrypted data until they are decrypted by authorized users. Specifically, the following steps are performed:

[0093] Homomorphic encryption technology allows calculations to be performed on encrypted data, and the calculation results remain encrypted. User data is encrypted and uploaded to a central server, which performs encrypted calculations. Homomorphic encryption technology includes partial homomorphic encryption and full homomorphic encryption.

[0094] Optimize the performance loss after homomorphic encryption, accelerate encryption calculations through hardware acceleration, and use parallel computing to distribute tasks to multiple nodes for processing;

[0095] User data is uploaded in encrypted form, and the central server performs encrypted calculations. The calculation results remain in encrypted form until the authorized user decrypts them;

[0096] Homomorphic encryption is applied to data computing: Homomorphic encryption technology (such as partial homomorphic encryption and fully homomorphic encryption) allows calculations to be performed on encrypted data, and the calculation results remain encrypted to ensure privacy protection.

[0097] User data is encrypted and uploaded to the server, which performs encryption calculations (such as addition, multiplication, etc.);

[0098] Encryption calculation formula:

[0099] E(f(D))=f(E(D));

[0100] Wherein, E(D) represents the encryption of data D, f(D) is the calculation function, and E(f(D)) represents the encrypted calculation result;

[0101] In order to optimize the performance loss caused by homomorphic encryption, hardware acceleration technology (such as TPU, GPU) can be used to accelerate encryption calculations.

[0102] Use parallel computing to distribute tasks to multiple nodes for processing, thus reducing computing time.

[0103] User data is uploaded in encrypted form, and the central server performs encrypted calculations, with the calculation results remaining in encrypted form until decrypted by authorized users.

[0104] Calculation formula:

[0105] E(f(D1,D2))=f(E(D1),E(D2));

[0106] Among them, E(D1) and E(D2) are the encryption of data D1 and D2 respectively, and the calculation result is still in encrypted form.

[0107] Step 40: Perform automated compliance rule audit based on smart contracts. The compliance rules will be embedded in smart contracts to automatically check whether the data processing behavior is legal. According to the blockchain network architecture and smart contracts and in response to the regionalized compliance control of cross-border data flow, it is determined that the data complies with the compliance requirements when flowing across borders, including:

[0108] Automatically audit the data processing process based on smart contracts. All data processing rules and privacy policies are embedded in smart contracts to automatically verify data access and processing behaviors.

[0109] Compliance controls in response to cross-border data flows through smart contracts;

[0110] The encryption strategy and storage location of data during flow are automatically adjusted by smart contracts;

[0111] Use smart contracts to automate audits of data processing to ensure that data processing complies with privacy protection regulations in various countries (such as GDPR and CCPA).

[0112] All data processing rules and privacy policies are embedded in smart contracts to automatically verify data access and processing behaviors.

[0113] Compliance check formula:

[0114] CompliantProcessing(Data,RegionComplianceRules)

[0115] →SmartContractVerify;

[0116] in,

[0117] Data is the data to be processed.

[0118] RegionComplianceRules is the compliance requirement of the region.

[0119] SmartContractVerify represents the verification of compliance by a smart contract.

[0120] Compliance controls for cross-border data flows are introduced through smart contracts to ensure that data complies with the data protection laws of the target country or region when flowing across borders.

[0121] The encryption strategy and storage location of data during flow are automatically adjusted by smart contracts to ensure compliance with local legal requirements.

[0122] Step 50: Implement fine-grained control of data access based on the blockchain network architecture and smart contracts. Authorized users are allowed to access data through blockchain verification. The blockchain records all access behaviors and finally strengthens privacy protection, including:

[0123] Fine-grained permission management based on blockchain network architecture. Users can only access authorized data. All access requests are verified through blockchain, and user permissions are dynamically adjusted according to different data types and roles.

[0124] Audit and permission behavior records, all user permission changes and data access logs are saved in the blockchain.

[0125] Use consortium chains or public chains (such as Ethereum or Hyperledger) to build a transparent management system to ensure that all data processing activities, privacy protection measures, and compliance audits are recorded on the blockchain.

[0126] The data in the blockchain cannot be tampered with. All data uploading, processing, querying and other behaviors must be verified by the blockchain to ensure the transparency and non-tamperability of the data processing process.

[0127] Use smart contracts to automatically execute privacy protection policies, dynamically control data access permissions, and record all data operation logs.

[0128] The blockchain records all access and processing behaviors on the chain, achieving real-time auditable access control, ensuring that all operations are traceable, and solving transparency issues.

[0129] Blockchain technology and smart contracts are used to achieve fine-grained permission control. Users can only access the data they are authorized to access, and all access requests are verified through the blockchain.

[0130] User permissions can be dynamically adjusted based on different data types and roles to ensure secure access to data.

[0131] Permission control formula:

[0132] GrantAccess(User,Data,PermissionType)→SmartContractExecute;

[0133] in,

[0134] User is the data accessor.

[0135] Data is the data to be accessed.

[0136] PermissionType is the permission type (such as read, write, etc.);

[0137] Each data access behavior is recorded through the blockchain to ensure audit and traceability, and prevent data abuse and abuse of permissions. All permission changes and data access logs are saved in the blockchain to ensure transparency and immutability.

[0138] Audit record formula:

[0139] AuditRecord(User,Data,ActionType)→BlockChainLedger;

[0140] ActionType is the access operation type (such as read, write, etc.),

[0141] User is the visitor;

[0142] BlockChainLedger is a blockchain ledger record.

[0143] By combining federated learning, zero-knowledge proof, homomorphic encryption and other technologies, data is encrypted and privacy-protected from beginning to end, which not only effectively avoids data leakage, but also completes data processing without decryption, ensuring maximum privacy protection.

[0144] By introducing blockchain technology, not only can the transparency of the data processing process be ensured, but also a complete audit traceability function can be provided. All processing, access and data flow are recorded through the blockchain to ensure that any improper behavior can be traced and discovered.

[0145] Through smart contracts and automated compliance checks, the system can detect legal compliance in the data processing process in real time and automatically comply with privacy protection regulations in different countries and regions, such as GDPR and CCPA. Especially when data flows across borders, it can ensure that the data complies with the laws of each region.

[0146] By using homomorphic encryption and hardware acceleration technology (such as GPU, TPU), even when performing complex calculations in an encrypted state, it is possible to significantly improve computing efficiency and alleviate the performance bottleneck caused by encrypted computing. The distributed computing model of federated learning further reduces the reliance on centralized storage and computing, reducing the pressure of centralized computing.

[0147] By combining blockchain with smart contracts to achieve fine-grained permission control, permissions can be dynamically adjusted according to user roles and data types to ensure that users can only access the data they are authorized to access. In addition, all permission management behaviors are recorded on the blockchain, enabling full auditing and traceability, further enhancing data security and compliance.

[0148] This invention can adapt to the ever-changing privacy protection needs. As technology develops and compliance requirements change, smart contracts can be flexibly modified to meet new privacy protection needs. In addition, the distributed architecture of federated learning supports the access of various new data sources and has strong scalability.

[0149] By combining zero-knowledge proof, homomorphic encryption and federated learning, not only can privacy be protected at the data level, but also the transparency and verifiability of the entire data processing process can be ensured through smart contracts and blockchain. Few inventions in the existing technology can protect privacy data so comprehensively and at so many levels.

[0150] The introduction of smart contracts to automatically conduct compliance audits. This blockchain-based "automatic audit" model can automatically verify compliance with regional compliance requirements at each stage of data processing, reducing manual review costs and compliance risks.

[0151] By utilizing the parallel computing optimization invention of homomorphic encryption, data privacy is maintained and computing efficiency is improved, which greatly reduces the computing bottleneck caused by traditional homomorphic encryption. The combination with federated learning avoids high latency in data transmission and improves overall computing efficiency.

[0152] Through innovative cross-border data flow compliance mechanisms and dynamic data encryption / decryption management inventions, data can be safely flowed between different countries and regions while complying with local data privacy laws and regulations. Existing privacy protection inventions often ignore cross-border compliance issues, and this invention significantly improves this.

[0153] The introduction of blockchain technology makes the entire data processing process no longer dependent on a centralized entity. At the same time, it can provide transparent records and real-time audit functions for all operations, effectively avoiding potential privacy leaks and data abuse issues.

[0154] Embodiment 2

[0155] like Figure 2 As shown, in order to solve the above technical problems, based on the first embodiment, another technical solution adopted by this application is: a privacy protection enhancement system in a data processing service, comprising the following steps:

[0156] The data acquisition module is used to obtain the service data to be processed, build a blockchain network architecture through a consortium chain or a public chain based on the service data to be processed, verify the data in the blockchain, perform data privacy protection and dynamically control data access rights based on smart contracts, and record all data operation logs;

[0157] The privacy-preserving data sharing module is used to implement federated learning on multiple distributed nodes and build privacy-preserving data sharing. Each node retains local data and adds noise to the uploaded model parameters through differential privacy to build a federated learning model. The zero-knowledge proof mechanism allows nodes to prove the legality of the calculation.

[0158] The calculation encryption data module is used to encrypt data according to homomorphic encryption technology. All calculation tasks are performed in an encrypted state, and the calculation results are encrypted data until they are decrypted by authorized users.

[0159] A compliance rules audit module is used to perform automated compliance rules audits based on smart contracts. The compliance rules will be embedded in smart contracts to automatically check whether data processing behaviors are legal. Based on the blockchain network architecture and smart contracts and in response to regionalized compliance controls on cross-border data flows, it is determined that data complies with compliance requirements when flowing across borders.

[0160] The fine-grained permission management and audit module is used to implement fine-grained control of data access based on the blockchain network architecture and smart contracts. Authorized users are allowed to access data through blockchain verification. The blockchain records all access behaviors and finally strengthens privacy protection.

[0161] Through federated learning, homomorphic encryption, smart contracts, and blockchain, computing efficiency, privacy protection, compliance support, and transparency have been greatly improved. Compared with existing technologies, this solution can better deal with privacy leakage risks, compliance issues, and abuse of authority in data processing, and provide more powerful technical support for future privacy protection needs.

[0162] The foregoing Figure 1 The various variations and specific examples of the privacy protection enhancement method in a data processing service in Example 1 are also applicable to the privacy protection enhancement system in a data processing service in this embodiment. Through the above detailed description of the privacy protection enhancement method in a data processing service, those skilled in the art can clearly know the implementation method of the privacy protection enhancement system in a data processing service in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0163] Embodiment 3

[0164] An embodiment of the present application provides a computer device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement a privacy protection enhancement method in a data processing service provided in the above method embodiment.

[0165] Figure 3The hardware structure diagram of a device for implementing a privacy protection enhancement method in a data processing service provided in an embodiment of the present application is shown. The device may participate in or include the apparatus or system provided in an embodiment of the present application. Figure 3 As shown, the computer device 10 may include one or more processors 1002 (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1004 for storing data, and a transmission device 1006 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations are shown.

[0166] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer device 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0167] The memory 1004 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to a privacy protection enhancement method in a data processing service in an embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 1004, that is, implementing the above-mentioned method. The memory 1004 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 1004 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer device 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0168] The transmission device 1006 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer device 10. In one example, the transmission device 1006 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 1006 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0169] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer device 10 (or mobile device).

[0170] Embodiment 4

[0171] An embodiment of the present application also provides a computer-readable storage medium, which can be set in a server to store at least one instruction or at least one program related to a privacy protection enhancement method in a data processing service in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement a privacy protection enhancement method in a data processing service provided in the above method embodiment.

[0172] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0173] Embodiment 5

[0174] The embodiment of the present invention also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. The processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes a privacy protection enhancement method in a data processing service provided in the above various optional implementations.

[0175] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0176] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0177] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware or by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0178] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, and its technical scope must be determined according to the scope of the claims.

[0179] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for enhancing privacy protection in a data processing service, characterized in that: The following steps are involved: Obtain the service data to be processed, build a blockchain network architecture through a consortium chain or a public chain based on the service data to be processed, verify the data in the blockchain, perform data privacy protection and dynamically control data access rights based on smart contracts, and record all data operation logs; Based on the implementation of federated learning on multiple distributed nodes, privacy-preserving data sharing is constructed. Each node retains local data, and noise is added to the uploaded model parameters through differential privacy. A federated learning model is constructed, and the nodes are allowed to prove the legality of the calculation through the zero-knowledge proof mechanism. Data is encrypted using homomorphic encryption technology. All computing tasks are performed in an encrypted state, and the computing results are encrypted data until they are decrypted by authorized users. Automated compliance audits based on smart contracts. The compliance rules will be embedded in smart contracts to automatically check whether data processing is legal. Based on the blockchain network architecture and smart contracts and in response to regionalized compliance controls on cross-border data flows, it is determined that data complies with compliance requirements when flowing across borders; Based on the blockchain network architecture and smart contracts, fine-grained control of data access is achieved. Authorized users are allowed to access data through blockchain verification. The blockchain records all access behaviors and finally strengthens privacy protection.

2. The method according to claim 1, characterized in that: The construction of privacy-preserving data sharing specifically includes: Federated learning on multiple distributed nodes, where each node only accesses and processes local data and aggregates the locally trained model parameters by periodically uploading them to the central server; Each time a local model update is uploaded, noise is added to the uploaded model parameters based on differential privacy. Based on zero-knowledge proof, the model update submitted by each node is verified to be compliant.

3. The method according to claim 1, characterized in that: The data is encrypted according to the homomorphic encryption technology, specifically including: Homomorphic encryption technology allows calculations to be performed on encrypted data, and the calculation results remain encrypted. User data is encrypted and uploaded to a central server, which performs encrypted calculations. Homomorphic encryption technology includes partial homomorphic encryption and full homomorphic encryption. Optimize the performance loss after homomorphic encryption, accelerate encryption calculations through hardware acceleration, and use parallel computing to distribute tasks to multiple nodes for processing; User data is uploaded in encrypted form, and the central server performs encrypted calculations, with the calculation results remaining in encrypted form until decrypted by authorized users.

4. The method according to claim 1, characterized in that: The automated compliance audit based on smart contracts specifically includes: Automatically audit the data processing process based on smart contracts. All data processing rules and privacy policies are embedded in smart contracts to automatically verify data access and processing behaviors. Compliance controls in response to cross-border data flows through smart contracts; The encryption strategy and storage location of the data during the flow are automatically adjusted by the smart contract.

5. The method according to claim 1, characterized in that: The fine-grained control of data access based on the blockchain network architecture and smart contracts specifically includes: Fine-grained permission management based on blockchain network architecture. Users can only access authorized data. All access requests are verified through blockchain, and user permissions are dynamically adjusted according to different data types and roles. Audit and permission behavior records, all user permission changes and data access logs are saved in the blockchain.

6. The method according to claim 1, characterized in that: The consortium chain or public chain includes Ethereum or Hyperledger; The data privacy protection is implemented according to the smart contract and the data access rights are dynamically controlled. The execution process formula is as follows: Execute Transaction(Data, Access Permissions, Compliance Rules); in: Data is data; Access Permissions is access rights; Compliance Rules are compliance rules.

7. The method according to claim 2, characterized in that: The model update formula is: in, is the model after training the i-th node, D i is the local data of the i-th node, θ i are the initial parameters for training.

8. A privacy protection enhancement system in a data processing service, applied to the privacy protection enhancement method in a data processing service as claimed in any one of claims 1 to 7, characterized in that: include: The data acquisition module is used to obtain the service data to be processed, build a blockchain network architecture through a consortium chain or a public chain based on the service data to be processed, verify the data in the blockchain, perform data privacy protection and dynamically control data access rights based on smart contracts, and record all data operation logs; The privacy-preserving data sharing module is used to implement federated learning on multiple distributed nodes and build privacy-preserving data sharing. Each node retains local data, adds noise to the uploaded model parameters through differential privacy, builds a federated learning model, and allows nodes to prove the legality of calculations through a zero-knowledge proof mechanism. The calculation encryption data module is used to encrypt data according to homomorphic encryption technology. All calculation tasks are performed in an encrypted state, and the calculation results are encrypted data until they are decrypted by authorized users. A compliance rules audit module is used to perform automated compliance rules audits based on smart contracts. The compliance rules will be embedded in smart contracts to automatically check whether data processing behaviors are legal. Based on the blockchain network architecture and smart contracts and in response to regionalized compliance controls on cross-border data flows, it is determined that data complies with compliance requirements when flowing across borders; The fine-grained permission management and audit module is used to implement fine-grained control of data access based on the blockchain network architecture and smart contracts. Authorized users are allowed to access data through blockchain verification. The blockchain records all access behaviors and finally strengthens privacy protection.

9. A computer device, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the privacy protection enhancement method in the data processing service as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the privacy protection enhancement method in the data processing service according to any one of claims 1 to 7.

Images