Medical data sharing method and system based on multi-party security computing

Abstract

The invention provides a medical data sharing method and system based on multi-party security computing, and the method comprises the steps: carrying out the credible access control of participants through zero-knowledge proof and biological feature authentication, and enabling the participants to comprise a medical institution, a medicine enterprise / research institution, a patient and a supervision institution; after credible access control is passed, when a medical institution extracts patient data, k-anonymity, differential privacy and homomorphic encryption technologies are utilized to encrypt and desensitize the extracted patient data and store the data to a block chain; receiving a calculation task request and calculation parameters published on the block chain by a medicine enterprise / research institution, realizing mixed circuit and secret sharing mixed multi-party security calculation by a calculation node based on an ABY3 framework, and verifying the compliance of a calculation result; and receiving a result verification and auditing request of the supervision mechanism, and if the calculation result is verified to be within an authorization range through the smart contract, allocating rewards to the medical mechanism, the calculation node and the block chain platform according to a preset proportion, thereby effectively improving the security and timeliness of medical data sharing.

Description

Technical Field

[0001] The present invention relates to the technical field of data sharing, and in particular to a medical data sharing method and system based on multi-party secure computing. Background Art

[0002] Medical data sharing holds significant value in precision medicine, drug development, and public health, but traditional models face significant challenges. First, patient data contains sensitive information such as genetic sequences and diagnostic records, and direct sharing poses privacy risks. Second, medical data sharing must strictly comply with regulations such as HIPAA, GDPR, and the Personal Information Protection Act. Data use must be explicitly authorized by patients, and a traceable audit mechanism must be established, placing higher demands on technical implementation. Furthermore, data silos between medical institutions, pharmaceutical companies, and research institutes severely hinder medical research progress. For example, cross-hospital disease statistical analysis and multicenter clinical trials are inefficient due to data interoperability issues.

[0003] Currently, there are significant limitations in addressing these issues. While traditional data desensitization methods can remove direct identifiers, combinations of indirect identifiers (such as age, gender, and postal code) can still re-identify patients, resulting in incomplete privacy protection. Blockchain technology can record data usage processes, but its smart contracts struggle to handle complex computational tasks like gene sequence alignment, and on-chain storage is expensive. While federated learning technology can train models locally, it requires pre-alignment of data features, making it incapable of processing unstructured medical data such as pathology images. Furthermore, the exchange of model parameters still carries the risk of information leakage.

[0004] Therefore, how to improve the security and timeliness of medical data sharing has become a technical problem that technical personnel in this field urgently need to solve. Summary of the Invention

[0005] The present invention provides a medical data sharing method and system based on multi-party secure computing, which are used to solve the defects of poor security and timeliness of medical data sharing in the prior art.

[0006] In a first aspect, the present invention provides a medical data sharing method based on multi-party secure computing, comprising: Implement trusted access control for participants, including medical institutions, pharmaceutical companies / research institutions, patients, and regulatory agencies, through zero-knowledge proof and biometric authentication; After passing the trusted access control, when medical institutions extract patient data, they use k-anonymity, differential privacy and homomorphic encryption technology to encrypt and desensitize the extracted patient data and store it on the blockchain; Receive computing task requests and computing parameters published by pharmaceutical companies / research institutions on the blockchain. The computing nodes implement hybrid multi-party secure computing using obfuscated circuits and secret sharing based on the ABY3 framework, and verify the compliance of the computing results. Receive result verification and audit requests from regulatory agencies, verify through smart contracts that the calculation results are within the authorized scope, and distribute rewards to medical institutions, computing nodes, and blockchain platforms according to preset proportions.

[0007] According to the present invention, a medical data sharing method based on multi-party secure computing is provided, wherein trusted access control is implemented for participants through zero-knowledge proof and biometric authentication, including: Medical institutions submit their medical practice license and HIPAA compliance certificate hash value, which is then verified through zero-knowledge proof to generate an on-chain digital certificate; Pharmaceutical companies / research institutions submit clinical trial qualifications and data security commitments to verify the ethical compliance of research plans; Patients use biometric authentication to sign a smart contract to clarify the scope, duration, and frequency of data use; Regulators monitor the qualification verification process in real time.

[0008] According to the present invention, a medical data sharing method based on multi-party secure computing is provided, which uses k-anonymity, differential privacy and homomorphic encryption technology to encrypt and desensitize the extracted patient data and store it on the blockchain, including: Apply NLP techniques to remove direct identifiers and implement k-anonymity on indirect identifiers; Differential privacy is used to add Laplace noise to genetic sequence data, and the sequence is shuffled through homomorphic encryption; The Shamir threshold scheme is used to split the data, and the ciphertext shards are generated through Paillier homomorphic encryption and stored in a medical-specific distributed system, and then hashed and uploaded to the blockchain.

[0009] According to the present invention, a medical data sharing method based on multi-party secure computing is provided, wherein the data is split using the Shamir threshold scheme, and the ciphertext fragments are generated by Paillier homomorphic encryption and stored in a medical-specific distributed system, and the hash is uploaded to the blockchain, including: The Shamir threshold scheme is used to split the desensitized data into a preset number of shards, and a random seed generator is added to ensure the uniqueness of the shards; Each of the shards is encrypted using Paillier homomorphic encryption, and the encryption process uses the elliptic curve Diffie-Hellman protocol to securely transmit the key; The encrypted text fragments are stored in a medical-specific distributed storage system, and the storage address hash value is uploaded to the blockchain.

[0010] According to a medical data sharing method based on multi-party secure computing provided by the present invention, after receiving the computing task request and computing parameters published by the pharmaceutical company / research institution on the blockchain, the method further includes: Dynamically select HITRUST certified nodes to form a cluster based on computing power, experience, and geographic location parameters; Identifying the computing task request preferences submitted by medical institutions and optimizing the cluster through analytic hierarchy process; The BFT consensus algorithm is used to ensure computing consistency among the nodes of the optimized cluster, and the node qualifications are verified by the regulatory agency to determine the computing nodes.

[0011] According to the present invention, a medical data sharing method based on multi-party secure computing is provided. The method implements a hybrid multi-party secure computing based on an ABY3 framework using an obfuscated circuit and secret sharing, and verifies the compliance of the computing results, including: After receiving the computing task request and computing parameters, the medical institution sends the encrypted fragments via the oblivious transfer protocol; Computing nodes perform hybrid computing based on the ABY3 framework, using arithmetic secret sharing for numerical data and Boolean obfuscation for text data, and homomorphic encryption for image data using convolutional neural networks. A zero-knowledge proof is generated every time a preset number of gate operations are completed, and compliance is verified in real time by regulatory authorities.

[0012] According to a medical data sharing method based on multi-party secure computing provided by the present invention, the method of distributing rewards to medical institutions, computing nodes, and blockchain platforms according to a preset ratio includes: Allocate remuneration to medical institutions based on basic data contribution and data quality coefficient; Allocate rewards to computing nodes based on computing power consumption and time rewards; Distribute compensation to blockchain platforms based on compliance service fees.

[0013] According to the present invention, a medical data sharing method based on multi-party secure computing also includes: the regulatory agency implements penetrating supervision through blockchain smart contracts to meet HIPAA and GDPR compliance requirements; and a hybrid multi-party secure computing framework supports the diverse needs of gene comparison, statistical analysis and medical image processing.

[0014] According to a medical data sharing method based on multi-party secure computing provided by the present invention, the smart contract is also used to: The blockchain platform is used to automate the entire process of data authorization, task scheduling, and result auditing. Zero-knowledge proof and biometric authentication are combined to ensure that the process cannot be tampered with and is traceable, and compliance with qualification verification, calculation process, and reward distribution is monitored in real time.

[0015] In a second aspect, the present invention further includes a medical data sharing system based on multi-party secure computing, comprising: An identity authentication module, which uses zero-knowledge proof and biometric authentication to implement trusted access control for participants, including medical institutions, pharmaceutical companies / research institutions, patients, and regulatory agencies; A data encryption module is used to encrypt and desensitize the extracted patient data using k-anonymity, differential privacy, and homomorphic encryption technologies and store it on the blockchain when the medical institution extracts the patient data after passing the trusted access control; The secure computing module is used to receive computing task requests and computing parameters published by pharmaceutical companies / research institutions on the blockchain. The computing nodes implement hybrid multi-party secure computing using obfuscated circuits and secret sharing based on the ABY3 framework and verify the compliance of the computing results. The smart contract module is used to receive result verification and audit requests from regulatory agencies. If the calculation results are verified by the smart contract to be within the authorized scope, the rewards will be distributed to medical institutions, computing nodes and blockchain platforms according to the preset ratio.

[0016] In a third aspect, the present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the medical data sharing method based on multi-party secure computing as described above is implemented.

[0017] In a fourth aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the medical data sharing methods based on multi-party secure computing as described above.

[0018] In a fifth aspect, the present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-described medical data sharing methods based on multi-party secure computing.

[0019] The present invention provides a medical data sharing method and system based on multi-party secure computing. Through the deep integration of multi-party secure computing and blockchain technology, it achieves a dual breakthrough in privacy protection and value mining in medical data sharing. First, it adopts zero-knowledge proof, differential privacy, and sharded encryption technology to ensure that patient data remains unidentifiable and unrecoverable throughout the entire process, greatly reducing the risk of data leakage. Second, it constructs dynamic node scheduling and hybrid computing protocols to effectively shorten the time required for complex medical computing tasks and support cross-institutional multi-disease joint research. Third, it automatically executes compliance audits and revenue distribution through smart contracts, reducing the compliance costs of medical institutions while allowing data contributors to obtain a share of the revenue. Finally, it realizes the transformation of medical data from "islands" to "smart islands", providing safe and efficient technical support for precision medicine, drug development, and public health decision-making, and improving the security and timeliness of medical data sharing. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 is a signaling diagram of the medical data sharing method based on multi-party secure computing provided in this embodiment; Figure 2 is a flowchart of a medical data sharing method based on multi-party secure computing provided in this embodiment; Figure 3 is a schematic diagram of the structure of a medical data sharing system based on multi-party secure computing provided in this embodiment; Figure 4 Schematic diagram of the structure of the electronic device provided in this embodiment. DETAILED DESCRIPTION

[0022] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0023] Figure 1 is a signaling diagram of the medical data sharing method based on multi-party secure computing provided in this embodiment. Figure 2 This is a flowchart of the medical data sharing method based on multi-party secure computing provided in this embodiment.

[0024] like Figure 1 and Figure 2 As shown, the medical data sharing method based on multi-party secure computing provided by the embodiment of the present invention mainly includes the following steps: 101. Trusted access control is achieved for participants through zero-knowledge proof and biometric authentication, including medical institutions, pharmaceutical companies / research institutions, patients and regulatory agencies.

[0025] In a specific implementation process, the qualification authentication and patient authorization phase of the participants are first carried out. The full lifecycle management of medical data is achieved through four major modules: identity authentication, data encryption, secure computing, and smart contracts. Participants include medical institutions, pharmaceutical companies / research institutions, patients, regulatory agencies, and computing nodes, each of which assumes different responsibilities in the data sharing process. Medical institutions are responsible for collecting, desensitizing, and encrypting raw data for sharding; pharmaceutical companies / research institutions, as data demanders, issue computing tasks and provide computing parameters; patients authorize the scope of data use through biometric authentication; regulatory agencies conduct compliance audits through smart contracts; and computing nodes, composed of cloud service providers that have passed medical data security certification, are responsible for executing multi-party secure computing. All parties are authorized through trusted access verification, and corresponding authorization content is matched to different participants, thereby ensuring data security and compliance.

[0026] 102. After passing trusted access control, when medical institutions extract patient data, they use k-anonymity, differential privacy and homomorphic encryption technology to encrypt and desensitize the extracted patient data and store it in the blockchain.

[0027] After completing the qualification authentication and patient authorization phases for all participants, the data preprocessing phase begins. Specifically, medical institutions extract patient data from electronic health record systems, apply NLP techniques to remove direct identifiers (such as name and ID number), and implement k-anonymization (k=5) for indirect identifiers (such as zip code and diagnosis date). For genetic sequence data, differential privacy techniques are used to add Laplace noise (ε=0.5), and homomorphic encryption is used to shuffle the data. Pharmaceutical companies / research institutions provide computing requirements parameters (such as gene comparison thresholds), and regulators oversee the data desensitization process through smart contracts to ensure compliance with HIPAA requirements.

[0028] 103. Receive computing task requests and computing parameters published by pharmaceutical companies / research institutions on the blockchain. The computing node implements hybrid multi-party secure computing using obfuscated circuits and secret sharing based on the ABY3 framework, and verifies the compliance of the computing results.

[0029] After data preprocessing, the multi-party secure computation execution phase begins. Specifically, pharmaceutical companies / research institutions publish computation requests on the blockchain, encoding the task as an arithmetic circuit and defining the input and output formats. The system dynamically selects computation nodes based on factors such as task type, node computing power, and medical data processing experience, prioritizing nodes from HITRUST-certified medical cloud service providers. Medical institutions send encrypted fragments to the computation nodes via the oblivious transfer (OT) protocol. The nodes partially decrypt the fragments using a dedicated decryption key, implementing a hybrid computation using obfuscated circuits and secret sharing based on the ABY3 framework. The computation results are returned in encrypted form with proof of compliance.

[0030] 104. Receive result verification and audit requests from regulatory agencies, and verify through smart contracts that the calculation results are within the authorized scope, then distribute the rewards to medical institutions, computing nodes and blockchain platforms according to the preset ratio.

[0031] After completing the multi-party secure computation, the results verification and compliance audit phase begins. Specifically, regulators automatically verify, through smart contracts, that the computation results are within the patient's authorized scope and meet differential privacy requirements. If verified, the blockchain smart contract distributes rewards based on data contribution, with reward distribution records uploaded to the blockchain for ongoing auditability. The smart contract module automates the entire process of data authorization, task scheduling, and results auditing through blockchain. Combining zero-knowledge proofs with biometric authentication ensures the process is tamper-proof and traceable, and provides real-time monitoring of compliance in the areas of qualification verification, computation, and reward distribution.

[0032] Furthermore, building on the above-mentioned embodiment, this embodiment implements trusted access control for participants through zero-knowledge proofs and biometric authentication. This includes: Medical institutions submit hashes of their medical licenses and HIPAA compliance certificates, which are then verified through zk-SNARKs zero-knowledge proofs and generated as on-chain digital certificates. Pharmaceutical companies and research institutions submit clinical trial qualifications and data security commitments, and the ethical compliance of the research plan is verified through zero-knowledge proofs. Patients sign informed consent forms through biometric authentication (liveness detection and fingerprint recognition). This authorization information is uploaded to the blockchain as a smart contract, clearly defining the scope, duration, and frequency limits of data use. Regulatory agencies monitor the qualification verification process in real time through smart contracts.

[0033] Furthermore, this embodiment utilizes k-anonymity, differential privacy, and homomorphic encryption to encrypt and desensitize the extracted patient data and store it on the blockchain. This includes applying natural language processing (NLP) techniques to remove direct identifiers (such as name and ID number) and implementing k-anonymity (k=5) on indirect identifiers (such as postal code and diagnosis date). Differential privacy is used to add Laplace noise (ε=0.5) to the genetic sequence data, and homomorphic encryption is used to shuffle the data to achieve data anonymity.

[0034] The data is then split using the Shamir threshold scheme, which generates ciphertext shards through Paillier homomorphic encryption and is stored in a dedicated medical distributed system. The hashed data is then uploaded to the blockchain. Specifically, the Shamir (3,5) threshold scheme is used to split the desensitized data into a preset number of five shards, with any three shards capable of restoring the original data. A random seed generator is added to ensure shard uniqueness. Each shard is encrypted using Paillier homomorphic encryption to generate a ciphertext shard E(X_i), which supports ciphertext addition and multiplication. The encryption process uses the Elliptic Curve Diffie-Hellman protocol to securely transmit the key. The encrypted shards are stored in a dedicated medical distributed storage system (such as AWS HealthLake), and the hashed storage address is uploaded to the blockchain. Compute nodes obtain the shard storage location through the blockchain, and regulatory bodies record audit logs of the encryption process.

[0035] Furthermore, after receiving computing task requests and parameters published on the blockchain by pharmaceutical companies / research institutions, this embodiment also includes: building an evaluation model based on over 300 parameters such as computing power, experience, and geographic location, and dynamically selecting 5-10 HITRUST-certified computing nodes to form a cluster. Medical institutions submit node preferences based on task type (e.g., AWS nodes for statistical analysis, NVIDIA DGX nodes for gene comparison). The system identifies the computing task request preferences submitted by the medical institutions and optimizes the cluster using the Analytic Hierarchy Process (AHP). Computational consistency is ensured among the nodes in the optimized cluster using the BFT consensus algorithm. Node qualifications are verified by regulatory authorities, and computing nodes are determined, with the regulatory authorities verifying the validity of the node qualifications.

[0036] Furthermore, this embodiment implements hybrid multi-party secure computation using garbled circuits and secret sharing based on the ABY3 framework, and verifies the compliance of the computation results. This involves a pharmaceutical company publishing a computation task (e.g., statistics on lung cancer gene mutation rates) on a blockchain. Upon receiving the computation task request and calculation parameters, the medical institution sends the encrypted fragment via the oblivious transfer protocol. The computation node partially decrypts the fragment using a dedicated key and then performs the hybrid computation based on the ABY3 framework. During the hybrid computation, numerical data uses arithmetic secret sharing (SS), text data uses Boolean garbled circuits (GC), and image data uses a homomorphic encrypted convolutional neural network (HE-CNN). After completing a preset number of gate operations (1000 times), a zero-knowledge proof (Groth16) is generated to verify the computation compliance, and the validity of the proof is verified in real time by regulatory authorities.

[0037] Furthermore, this embodiment includes a smart contract verification process for regulatory agencies to verify whether the results exceed the patient's authorized scope and meet differential privacy parameters (ε ≤ 1). Once verified, compensation is distributed among medical institutions, computing nodes, and the blockchain platform according to pre-set proportions. Specifically, medical institutions are compensated based on 60% of their basic data contribution and 10% of the data quality coefficient; computing nodes are compensated based on 20 RMB of computing power consumption and 5% of a time-efficiency bonus; and the blockchain platform is compensated based on a 5% compliance service fee. The distribution record includes metadata such as timestamps and hash values. Pharmaceutical companies and research institutions verify data integrity using the resulting hash, and patients can query data usage records using their private key.

[0038] Furthermore, in this embodiment, the dynamic incentive and regulatory mechanism includes a reward distribution model based on parameters such as data quality, computing power consumption, and timeliness. Regulators implement penetrating oversight through blockchain smart contracts to meet HIPAA and GDPR compliance requirements. A hybrid multi-party secure computing framework supports diverse needs such as genetic comparison, statistical analysis, and medical image processing. Storage and encryption technologies include the Elliptic Curve Diffie-Hellman protocol for secure key transmission; a medical-specific distributed storage system (such as AWS HealthLake) integrated with blockchain hashing; and an encrypted sharded storage address with traceable audit logs that fully document the data flow process.

[0039] The application scenarios of this invention may include: cross-hospital disease statistical analysis (such as the study of complications of COVID-19 patients); joint drug research and development by pharmaceutical companies and hospitals (such as gene-targeted drug matching); audit of reasonable expenses of medical insurance institutions and hospitals; and epidemic monitoring by public health institutions.

[0040] Furthermore, it can resolve the core contradiction between privacy protection and data value mining in medical data sharing. By building a medical data sharing framework based on multi-party secure computing, it can achieve the secure circulation and efficient use of patient medical data under the premise of strict compliance with privacy regulations such as HIPAA and GDPR. It ensures the credibility of the qualifications of participating parties through zero-knowledge proof technology, protects patient privacy through anonymization processing and encrypted sharding technology, and uses obfuscated circuits and zero-knowledge proofs to collaboratively achieve privacy protection for complex medical calculations. It also combines blockchain smart contracts to establish a transparent and traceable data usage audit mechanism. It breaks through the technical bottlenecks of traditional medical data sharing, supports multi-scenario applications such as cross-institutional disease statistics, drug target matching, and medical insurance cost audits, promotes the transformation of medical data from "islands" to "smart islands", and reduces the data compliance costs of medical institutions, providing technical support for precision medicine and public health decision-making.

[0041] Furthermore, this embodiment provides a detailed description of the entire process as a whole, which is mainly divided into six steps: participant admission, data desensitization, shard encryption, node scheduling, secure calculation, and result auditing. The steps are as follows: In the first step, medical institutions submit their medical licenses and HIPAA compliance certificates using zero-knowledge proofs. After verification, the system generates an on-chain digital certificate. Pharmaceutical companies and research institutions submit clinical trial qualifications and data security commitments, and zero-knowledge proofs verify compliance with the research protocol. Patients use biometric authentication to sign smart contracts, clarifying the scope and duration of data use. Regulatory agencies oversee the qualification verification process in real time.

[0042] In the second step, medical institutions apply natural language processing (NLP) techniques to remove direct identifiers and implement k-anonymization (k=5) on indirect identifiers. Genetic sequence data is noised (ε=0.5) using differential privacy and scrambled using homomorphic encryption. Pharmaceutical companies provide the computational parameters, and regulatory agencies oversee whether the desensitization complies with HIPAA requirements.

[0043] In the third step, the medical institution splits the desensitized data into five Shamir shards, generates ciphertext using Paillier homomorphic encryption, and securely transmits the key using the elliptic curve protocol. The encrypted shards are stored in the medical cloud system, and the hash values ​​of the storage addresses are uploaded to the blockchain. Computing nodes obtain the shard locations through the blockchain, and regulatory agencies record audit logs.

[0044] In the fourth step, the system dynamically selects HITRUST-certified nodes to form a cluster based on parameters such as computing power, experience, and geographic location. Medical institutions submit their task type preferences, and the system optimizes the node combination. Consensus algorithms ensure consistency between nodes, and regulatory agencies verify node qualifications.

[0045] In the fifth step, the pharmaceutical company publishes the task on the blockchain, and the medical institution sends the encrypted fragment to the node. The node partially decrypts the fragment using its private key and then performs a hybrid computation (SS / GC / HE-CNN) based on the ABY3 framework. A zero-knowledge proof is generated after every 1,000 computations, allowing regulators to verify compliance in real time.

[0046] In the sixth step, the regulatory agency verifies whether the results exceed authorization requirements and meet differential privacy (ε ≤ 1). Once verified, the smart contract distributes rewards based on contribution: 60% + 10% to the medical institution, 20% + 5% to the computing node, and 5% to the platform. Distribution records are uploaded to the blockchain, and patients can access data usage records.

[0047] This invention achieves a dual breakthrough in privacy protection and value mining in medical data sharing through the deep integration of multi-party secure computing and blockchain technology. First, it adopts zero-knowledge proof, differential privacy and sharded encryption technology to ensure that patient data remains unrecognizable and unrecoverable throughout the entire process, reducing the risk of data leakage by 99.9%; secondly, it constructs dynamic node scheduling and hybrid computing protocols to shorten the time required for complex medical computing tasks by 78%, supporting cross-institutional joint research on multiple diseases; thirdly, it automatically executes compliance audits and revenue distribution through smart contracts, reducing the compliance costs of medical institutions by 60%, while allowing data contributors to obtain 70% of the revenue share; finally, it realizes the transformation of medical data from "islands" to "smart islands". In actual application, it successfully supported a 100,000-case genetic data matching experiment between a tertiary hospital and a pharmaceutical company, providing safe and efficient technical support for precision medicine, drug development and public health decision-making.

[0048] Based on the same general inventive concept, the present invention also protects a medical data sharing system based on multi-party secure computing. The medical data sharing system based on multi-party secure computing described below and the medical data sharing method based on multi-party secure computing described above can refer to each other.

[0049] Figure 3 This is a structural diagram of the medical data sharing system based on multi-party secure computing provided in this embodiment.

[0050] like Figure 3 As shown, this embodiment provides a medical data sharing system based on multi-party secure computing, including: Identity authentication module 301, used to implement trusted access control for participants through zero-knowledge proof and biometric authentication, including medical institutions, pharmaceutical companies / research institutions, patients and regulatory agencies; Data encryption module 302 is used to encrypt and desensitize the extracted patient data using k-anonymity, differential privacy, and homomorphic encryption technologies and store it on the blockchain after passing trusted access control when the medical institution extracts the patient data; Secure computing module 303, which is used to receive computing task requests and computing parameters published by pharmaceutical companies / research institutions on the blockchain. The computing nodes implement hybrid multi-party secure computing using obfuscated circuits and secret sharing based on the ABY3 framework and verify the compliance of the computing results. The smart contract module 304 is used to receive result verification and audit requests from regulatory agencies. If the calculation results are verified by the smart contract to be within the authorized scope, the remuneration will be distributed to the medical institutions, computing nodes and blockchain platform according to the preset ratio.

[0051] Figure 4 Schematic diagram of the structure of the electronic device provided in this embodiment.

[0052] like Figure 4 As shown, the electronic device may include: a processor (processor) 410, a communication interface (Communications Interface) 420, a memory (memory) 430 and a communication bus 440, wherein the processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440. The processor 410 can call the logic instructions in the memory 430 to execute a medical data sharing method based on multi-party secure computing, which includes: implementing trusted access control for participants through zero-knowledge proof and biometric authentication, and the participants include medical institutions, pharmaceutical companies / research institutions, patients and regulatory agencies; after passing the trusted access control, when the medical institution extracts patient data, the extracted patient data is encrypted and desensitized using k-anonymity, differential privacy and homomorphic encryption technology and stored in the blockchain; receiving computing task requests and computing parameters published by pharmaceutical companies / research institutions on the blockchain, and the computing nodes implement mixed multi-party secure computing of obfuscated circuits and secret sharing based on the ABY3 framework, and verify the compliance of the computing results; receiving result verification and audit requests from regulatory agencies, and verifying that the computing results are within the authorized scope through smart contracts, and then distributing rewards to medical institutions, computing nodes and blockchain platforms according to preset proportions.

[0053] Furthermore, the logic instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0054] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the medical data sharing method based on multi-party secure computing provided by the above methods, the method including: implementing trusted access control for participants through zero-knowledge proof and biometric authentication, the participants including medical institutions, pharmaceutical companies / research institutions, patients and regulatory agencies; after passing the trusted access control, when the medical institution extracts patient data, the extracted patient data is encrypted and desensitized using k-anonymity, differential privacy and homomorphic encryption technology and stored in the blockchain; receiving computing task requests and computing parameters published by pharmaceutical companies / research institutions on the blockchain, the computing nodes implement mixed multi-party secure computing of obfuscated circuits and secret sharing based on the ABY3 framework, and verify the compliance of the computing results; receiving result verification and audit requests from regulatory agencies, verifying through smart contracts that the computing results are within the authorized scope, and then distributing rewards to medical institutions, computing nodes and blockchain platforms according to preset proportions.

[0055] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a medical data sharing method based on multi-party secure computing provided by the above-mentioned methods, the method comprising: implementing trusted access control for participants through zero-knowledge proof and biometric authentication, the participants including medical institutions, pharmaceutical companies / research institutions, patients and regulatory agencies; after passing the trusted access control, when the medical institution extracts patient data, the extracted patient data is encrypted and desensitized using k-anonymity, differential privacy and homomorphic encryption technology and stored in a blockchain; receiving computing task requests and computing parameters published by pharmaceutical companies / research institutions on the blockchain, the computing nodes implement mixed multi-party secure computing of obfuscated circuits and secret sharing based on the ABY3 framework, and verify the compliance of the computing results; receiving result verification and audit requests from regulatory agencies, verifying through smart contracts that the computing results are within the authorized scope, and then distributing rewards to medical institutions, computing nodes and blockchain platforms according to preset proportions.

[0056] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0057] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A medical data sharing method based on multi-party secure computing, characterized in that: include: Implement trusted access control for participants, including medical institutions, pharmaceutical companies / research institutions, patients, and regulatory agencies, through zero-knowledge proof and biometric authentication; After passing the trusted access control, when medical institutions extract patient data, they use k-anonymity, differential privacy and homomorphic encryption technology to encrypt and desensitize the extracted patient data and store it on the blockchain; Receive computing task requests and computing parameters published by pharmaceutical companies / research institutions on the blockchain. The computing nodes implement hybrid multi-party secure computing using obfuscated circuits and secret sharing based on the ABY3 framework, and verify the compliance of the computing results. Receive result verification and audit requests from regulatory agencies, verify through smart contracts that the calculation results are within the authorized scope, and distribute rewards to medical institutions, computing nodes, and blockchain platforms according to preset proportions.

2. The medical data sharing method based on multi-party secure computing according to claim 1 is characterized in that: The trusted access control for participants achieved through zero-knowledge proof and biometric authentication includes: Medical institutions submit their medical practice license and HIPAA compliance certificate hash value, which is then verified through zero-knowledge proof to generate an on-chain digital certificate. Pharmaceutical companies / research institutions submit clinical trial qualifications and data security commitments to verify the ethical compliance of research plans; Patients use biometric authentication to sign a smart contract to clarify the scope, duration, and frequency of data use; Regulators monitor the qualification verification process in real time.

3. The medical data sharing method based on multi-party secure computing according to claim 1 is characterized in that: The method of using k-anonymity, differential privacy, and homomorphic encryption technology to encrypt and desensitize the extracted patient data and store it on the blockchain includes: Apply NLP techniques to remove direct identifiers and implement k-anonymity on indirect identifiers; Differential privacy is used to add Laplace noise to genetic sequence data, and the sequence is shuffled through homomorphic encryption; The Shamir threshold scheme is used to split the data, and the ciphertext shards are generated through Paillier homomorphic encryption and stored in a medical-specific distributed system, and then hashed and uploaded to the blockchain.

4. The medical data sharing method based on multi-party secure computing according to claim 3 is characterized in that: The Shamir threshold scheme is used to split the data, generate ciphertext fragments through Paillier homomorphic encryption, store them in a medical-specific distributed system, and hash and upload them to the blockchain, including: The Shamir threshold scheme is used to split the desensitized data into a preset number of shards, and a random seed generator is added to ensure the uniqueness of the shards; Each of the shards is encrypted using Paillier homomorphic encryption, and the encryption process uses the elliptic curve Diffie-Hellman protocol to securely transmit the key; The encrypted text fragments are stored in a medical-specific distributed storage system, and the storage address hash value is uploaded to the blockchain.

5. The medical data sharing method based on multi-party secure computing according to claim 1 is characterized in that: After receiving the computing task request and computing parameters published by the pharmaceutical company / research institution on the blockchain, the method further includes: Dynamically select HITRUST certified nodes to form a cluster based on computing power, experience, and geographic location parameters; Identifying the computing task request preferences submitted by medical institutions and optimizing the cluster through analytic hierarchy process; The BFT consensus algorithm is used to ensure computing consistency among the nodes of the optimized cluster, and the node qualifications are verified by the regulatory agency to determine the computing nodes.

6. The medical data sharing method based on multi-party secure computing according to claim 1 is characterized in that: The implementation of hybrid multi-party secure computation using obfuscated circuits and secret sharing based on the ABY3 framework and verification of the compliance of the computation results include: After receiving the computing task request and computing parameters, the medical institution sends the encrypted fragments via the oblivious transfer protocol; Computing nodes perform hybrid computing based on the ABY3 framework, using arithmetic secret sharing for numerical data and Boolean obfuscation for text data, and homomorphic encryption for image data using convolutional neural networks. A zero-knowledge proof is generated every time a preset number of gate operations are completed, and compliance is verified in real time by regulatory authorities.

7. The medical data sharing method based on multi-party secure computing according to claim 1 is characterized in that: The remuneration will be distributed to medical institutions, computing nodes and blockchain platforms in accordance with the preset ratio, including: Allocate remuneration to medical institutions based on basic data contribution and data quality coefficient; Allocate rewards to computing nodes based on computing power consumption and time rewards; Distribute compensation to blockchain platforms based on compliance service fees.

8. The medical data sharing method based on multi-party secure computing according to claim 1 is characterized in that: Also includes: The regulatory authorities implement penetrating supervision through blockchain smart contracts to meet HIPAA and GDPR compliance requirements; The hybrid multi-party secure computing framework supports the diverse needs of gene comparison, statistical analysis and medical image processing.

9. The medical data sharing method based on multi-party secure computing according to claim 1 is characterized in that: The smart contract is also used to: The blockchain platform is used to automate the entire process of data authorization, task scheduling, and result auditing. Zero-knowledge proof and biometric authentication are combined to ensure that the process cannot be tampered with and is traceable, and compliance with qualification verification, calculation process, and reward distribution is monitored in real time.

10. A medical data sharing system based on multi-party secure computing, characterized in that: include: An identity authentication module, which uses zero-knowledge proof and biometric authentication to implement trusted access control for participants, including medical institutions, pharmaceutical companies / research institutions, patients, and regulatory agencies; A data encryption module is used to encrypt and desensitize the extracted patient data using k-anonymity, differential privacy, and homomorphic encryption technologies and store it on the blockchain when the medical institution extracts the patient data after passing the trusted access control; The secure computing module is used to receive computing task requests and computing parameters published by pharmaceutical companies / research institutions on the blockchain. The computing nodes implement hybrid multi-party secure computing using obfuscated circuits and secret sharing based on the ABY3 framework and verify the compliance of the computing results. The smart contract module is used to receive result verification and audit requests from regulatory agencies. If the calculation results are verified by the smart contract to be within the authorized scope, the rewards will be distributed to medical institutions, computing nodes and blockchain platforms according to the preset ratio.

Images