44 results about "Secure multi-party computation" patented technology

This application provides a digital resource processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product, belonging to the field of data processing technology. The digital resource processing method includes: associating and storing an encrypted aggregated digital resource value with a target cross-platform identity identifier of a target object; the encrypted aggregated digital resource value is generated by a secure multi-party computing cluster in encrypted state through collaborative computation of encrypted digital resource values ​​provided by several platforms; upon receiving a query request and confirming that the requester is the holder of the target cross-platform identity identifier, retrieving the encrypted aggregated digital resource value and sending it to the secure multi-party computing cluster for collaborative decryption, returning the decrypted aggregated digital resource value; and responding to the requester's digital resource exchange request by executing a digital resource exchange operation. The technical solution of this application can effectively protect data privacy while jointly using digital resources from multiple platforms.

This invention provides a cross-institutional collaborative data computation method based on secure multi-party computation, belonging to the field of data security and privacy protection technology. The method includes: each participating institution registering its identity and data metadata; the task initiator publishing a computation task description; performing operator-level decomposition on the objective function to obtain efficiency, overhead, and security strength indicators for each candidate protocol; using the security strength indicators to correct the efficiency and overhead indicators, weighted summing to obtain a comprehensive score, selecting the optimal protocol accordingly, and generating a hybrid protocol graph and execution plan; performing collaborative computation in stages, with protocol conversion at transition points; finally, the share is sent to the settlement node, aggregated and reconstructed to obtain plaintext results, and generating verifiable proofs. This invention achieves dynamic adaptation of protocols and tasks, optimization of security and performance balance, verifiable results, and dynamic adaptive scheduling.

The application provides a transformer holographic intelligent test method and system, belongs to the field of transformer testing and state evaluation, and is used for solving the problems of test system module fragmentation, information island, low data reliability and low scheduling efficiency in the related art. The application unifies the representation of test resource state, transformer physical behavior, safety risk and health degradation trend by constructing a physical information neural random field global model; realizes model collaborative updating under multi-station data privacy protection by using a federal security multi-party computing protocol; realizes trusted evidence preservation of key states and token economy closed loop by using a trusted execution environment and a directed acyclic graph-based distributed ledger; realizes adaptive optimization of resource scheduling by coupling Bayesian optimization and token price dynamics. The application can significantly improve the intelligent level, data reliability and resource utilization efficiency of transformer testing.

Systems and methods for validating analytics or machine learning models using secure multi-party computation (SMPC) are disclosed. The system operates with a data owner party providing a validation data set and an analytic owner party supplying a specification of the analytic or machine learning model. The analytic owner party converts the specification into an oblivious computation and compiles it into a circuit of operations compatible with an SMPC protocol. The data owner party downloads the compiled specification and constructs a validation circuit to execute the model against the validation data set without revealing the data or model details. The results of the SMPC are evaluated to produce performance statistics of the model, ensuring privacy for both parties' data throughout the process.

This invention discloses a heterogeneous government data collection and analysis system based on data governance and privacy protection, belonging to the field of intelligent analysis technology. The system includes: a data collection and cleaning module, which intelligently collects and cleans heterogeneous government data using adaptive algorithms; a privacy protection and dynamic desensitization module, which achieves comprehensive data privacy protection through dynamic desensitization technology and secure multi-party computation technology; an intelligent analysis and collaborative computing module, which, by introducing federated learning technology, enables multi-party collaborative model training without sharing original data, and shares the learned model parameters to achieve cross-departmental and cross-regional joint data analysis; and a data sharing and management module, which establishes a cross-departmental data sharing and verification mechanism through blockchain technology to ensure the transparency and traceability of data exchange. This invention can achieve efficient and intelligent government data collection, privacy protection, and analysis with low resource consumption.

The application provides a geographic information data analysis method and system based on a blockchain and federated learning, an electronic device and a storage medium, relates to the technical field of geographic information intelligent analysis, and the geographic information data analysis method and system based on the blockchain and federated learning are characterized in that geographic spatial data of a target monitoring area is acquired and converted into structured data with geographic coordinates, a geographic partition topology structure is constructed by setting an edge node according to the coordinates, nodes are grouped into blockchain fragments by generating geographic grid codes, an edge node in a fragment performs federated learning to generate an update amount, and the update amount is integrated into a fragment update amount after interaction verification; a secure multi-party computation is used to aggregate the fragment update amount to generate a global model through a preset program; the model is segmented and then synchronized to an edge node for reorganization, and new data is processed to output an analysis result, so that the geographic spatial data can be effectively analyzed and the result can be output by combining the blockchain and federated learning, through a series of data processing, node interaction and model operation.

A collaborative diagnostic method and system for equipment faults based on secure multi-party computation is disclosed, relating to data processing systems or methods applicable to administrative, commercial, financial, management, supervisory, or predictive purposes. The method includes: acquiring equipment operating data within each security domain; generating fault feature summaries by grouping data according to equipment type and parameter ranges; calculating multidimensional similarity of fault features between domains based on equipment type consistency, overlap of state feature ranges, and time delay; constructing a cross-domain fault propagation network; identifying fault loop propagation paths and fault convergence nodes; and finally outputting the analysis results. Implementing this method can improve the accuracy of identifying cross-domain fault propagation paths and key nodes without sharing raw data details across security domains.

Systems and methods for secure multiparty computation (MPC) over blockchain that packs messages into blockchain transactions are provided. MPC can be over Algorand blockchain that packs messages into Algorand transactions and utilizes its fast gossip protocol to transmit them efficiently among MPC parties (e.g., MPC nodes). The messages can be appended to a note field in the respective Algorand transactions.

This invention relates to the field of cloud computing technology, and particularly to a cross-domain data collaborative computing method based on secure multi-party computation and differential privacy. The invention proposes the following scheme: the task initiator abstracts the collaborative task into an intent description object and compiles it into an intermediate representation with gating logic, generating a dense-state function load for joint evaluation by multiple parties; the task assisting end generates real local contributions and counterfactual comparison contributions locally based on private data, and forms a detection score according to the request trajectory, adaptively determining the mixing coefficients. The two types of contributions are then subjected to restricted mixing and direction correction processing before participating in the dense-state computation. This application, without changing the appearance of the evaluation protocol, balances task intent protection and sensitive subgroup existence protection, improving security and engineering usability in cross-domain collaborative scenarios.

The application provides a residential energy system optimal control method based on data safe transmission, comprising: establishing a residential energy system model; obtaining electricity price, residential load and total cost function at each moment; taking minimizing the value of the total cost function as a target, iteratively optimizing the residential energy control sub-model to obtain an optimal residential energy control strategy; controlling and scheduling the residential energy according to the optimal residential energy control strategy; in the scheduling process, storing the optimal control data into a corresponding database in the blockchain after encryption; a queryer queries the data of each database in the blockchain through a proxy re-encryption mechanism and calculates in a secure multi-party calculation mode; the application can effectively perform optimal control on the residential energy; in addition, the application also introduces the blockchain technology, realizes safe encryption collection, transmission and interaction of the decentralized, tamper-proof, controllable and traceable residential energy optimal control data.

This invention presents a confidential image similarity determination method, belonging to the field of collaborative computation technology for multi-party privacy data. To address the low execution efficiency of existing secure multi-party computation methods for image similarity determination, and the significant impact on efficiency with increasing data volume, this invention combines the Paillier homomorphic encryption algorithm with Gödel coding technology to design a confidential image similarity determination protocol under a semi-honest model. The security and correctness of the protocol are analyzed. Furthermore, this invention designs a confidential image similarity determination protocol under a malicious model. This protocol uses zero-knowledge proofs and a segmentation-selection method to detect malicious behavior, and its security is proven using an ideal-practical paradigm. Verification shows that this invention exhibits very good execution efficiency.

The application discloses a kind of real-time health risk prediction method and system based on dynamic knowledge graph, it is related to medical information technology field.The method includes: multi-modal fusion and privacy protection preprocessing are carried out to medical care heterogeneous data, the semantic consistency of cross-institutional data is realized based on the entity alignment method of cross-modal graph neural network;Based on the hierarchical federated learning framework, the initial global model is generated by hierarchical encryption aggregation local model parameters through secure multi-party computation protocol, and the prediction distribution of global model is optimized in combination with the knowledge distillation of differential privacy constraint;Design noise robust gradient difference dynamic update trigger mechanism, smooth noise interference through sliding window mean, realize adaptive threshold calibration by linkage model performance verification;Redundant edge pruning based on confidence and 8-bit symmetric quantization realize lightweight deployment \ Real-time inference.The application significantly improves the real-time and accuracy of health risk prediction under the premise of protecting data privacy, and is suitable for cross-institutional medical care collaborative decision-making scenarios.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating differential privacy noise. One example method includes generating, by a first party of two or more parties participating in a secure multiparty computation (MPC) instance, a first l-bit random number, where l is a positive integer; comparing a XOR result of the first l-bit random number and a second l-bit random number with an integer determined based on a target probability of a Bernoulli distribution, where the comparing comprises performing a comparison protocol based on oblivious transfer; and determining a Bernoulli sampling of a random number based on a result of the comparing. The Bernoulli sampling of the random number can be used to generate a random noise value, which can be added to an MPC computation result according to a differential privacy mechanism.

Provided in the present invention are a decentralized hierarchical federated learning method and system, and an edge server. The method comprises: a plurality of edge servers respectively receiving gradient ciphertexts sent by different participant clients; the plurality of edge servers aggregating the received gradient ciphertexts on the basis of a secure multi-party computation protocol, so as to obtain an aggregated model ciphertext, wherein the secure multi-party computation protocol refers, in a mutually untrusted multi-user network, to a plurality of edge servers respectively holding different gradient ciphertexts jointly performing computation to obtain an aggregated model ciphertext based on these gradient ciphertexts, and each edge server only partially obtaining data in the aggregated model ciphertext, and not leaking its own gradient ciphertext to other edge servers; and the edge servers issuing the aggregated model ciphertext to the participant clients. By using the solution of the present invention, the security of model aggregation can be improved.

The present disclosure involves methods, apparatus, and systems for processing comparison in secure multi-party computation. One example method includes, partitioning a first difference (x) between a first share of value a and a first share of value b into N sections, and determining whether a<b based on first indicators and second indicators corresponding to the N sections. The first indicators include a first indicator indicating a comparison result between xj and yj computed based on a Vector Oblivious Shift Evaluation (VOSE) protocol, where xj is a jth section of x, and yj is a jth section of N sections of a second difference (y) between a second secret share of b and a second secret share of a. The second indicators include a second indicator indicating whether xj is a most significant section among sections of the first difference where xj≠yj.

The application relates to a data use control method, device, equipment and medium, and belongs to the technical field of data security. The method comprises the following steps: acquiring a digital contract and analyzing the digital contract to obtain a data use control strategy; the data use control strategy is split into multiple strategy segments; the strategy segments are encrypted and distributed to corresponding strategy storage nodes; when a data user initiates a data use operation, data use operation information is acquired and disassembled to obtain multiple pieces of to-be-verified information; the to-be-verified information is encrypted and sent to the corresponding strategy storage nodes; each strategy storage node performs collaborative calculation on the encrypted strategy segments and the encrypted to-be-verified information based on a secure multi-party computation protocol to obtain an authorization decision result; and the access permission of the data use operation is determined based on the authorization decision result. The application has the effect of improving the data security and privacy protection level.

The application provides a method and system for securely calculating the number of data greater than or less than the average in a multi-party secure calculation, belonging to the field of multi-party secure calculation, and used for providing a new scheme for achieving the task of securely calculating the number of data greater than or less than the average in a data group, wherein the multi-party includes an initiator of a calculation task, a referee and a plurality of participants, the participants and the initiator hold private data, the initiator and the referee are two different parties, and the method comprises the following steps: the participants pre-process the data, the referee generates a public key and a private key, and sends the public key to the participants, all the participants calculate the average of the private data based on an additive homomorphic encryption algorithm, and calculate the size relationship between the private data and the average based on a subtraction homomorphic encryption algorithm combined with the average, and then determine the number of data greater than or less than the average, and guarantee the data security of the private data held by all the participants.

The application relates to the technical field of solar photovoltaic power generation, and particularly discloses a multi-level secure data resource pool construction method for photovoltaic power prediction. The application ensures clear and traceable data ownership through data DNA fingerprints and smart contracts, effectively protecting the legal rights and interests and data sovereignty of data subjects. In combination with hierarchical differential privacy and a federal learning architecture, cross-domain collaborative training is realized, photovoltaic power prediction accuracy is improved, mathematical privacy protection is provided, advanced attacks such as model reverse are resisted, and data "available but invisible" is achieved. Based on a Shapley value and a multi-dimensional quality evaluation dynamic incentive mechanism, high-quality data contribution is encouraged, and the overall quality and availability of the data resource pool are improved. Through attribute-based dynamic access control and secure multi-party computation, fine-grained and context-aware permission management is realized, and the safety of core parameters is protected, so that the data sharing willingness and collaborative efficiency are significantly improved.

According to one aspect, a method for secure multi-party computation of high-frequency hits in differential privacy may include: receiving candidate values; incrementing the corresponding count in response to a received candidate value matching an entry in a table; adding an entry to the table in response to a received candidate value not matching an entry in the table and the table not exceeding a threshold size; decrementing the count in the table and deleting entries with a count of zero in response to a received candidate value not matching an entry in the table and the table exceeding a threshold size; adding noise to the corresponding counts of entries in the table and deleting any noisy corresponding counts less than a threshold; and outputting at least a portion of the table as a set of the top k values.

This application provides a distributed management method and system for big data in pharmaceutical supply chain distribution and settlement. Through distributed ledger storage and cross-verification, it establishes a trusted data foundation for workers from various parties involved in multi-source heterogeneous settlement data. Specifically, steps S131-S134 ensure the effectiveness of cross-verification, and random verification combined with exponential expansion of verification objects ensures the security of the verification process itself and effectively prevents verification errors. By integrating secure multi-party computation with a consensus-based global settlement rule model, it achieves privacy-preserving intelligent settlement where data is usable but not visible. While protecting core business secrets such as prices and sales volume, it ensures the automatic and accurate calculation of complex rules, enhancing the value of multi-party data fusion.

The application provides a threshold privacy set intersection method and device and a readable storage medium thereof, and belongs to the technical field of privacy calculation and secure multi-party computation. In view of the problems of low batch selection efficiency, large calculation and communication cost of the existing scheme in large-scale two-party balanced set matching, the application encodes a plurality of selection indexes of a receiving party into roots of blind polynomials on a finite field, realizes batch selection expression and key generation through polynomial coefficient transmission, and completes polynomial batch inadvertent transmission expansion; the algebraic association relationship established in the inadvertent transmission expansion stage is reused as the key material of an inadvertent pseudo-random function, pseudo-random labels of local calculation elements are obtained by both parties, and light batch inadvertent pseudo-random function mapping is completed; finally, the size of the intersection set is safely calculated in the label space, and whether to output the accurate intersection set is determined according to the comparison result of the size and the threshold. The application is mainly used for digital advertising audience evaluation, joint marketing and anti-fraud risk control.

The present specification discloses a secure service execution method and device, secret data as private information is divided into first secret data held by a first party and second secret data held by a second party in a shared form, the first party participating in secure multi-party computation generates a third intermediate number and a fourth intermediate number according to the first secret data and a first random number obtained from a third party, and sends the third intermediate number and the fourth intermediate number to the second party, so that the second party determines a second carry value and a second conversion parameter, and receives a first intermediate number and a second intermediate number sent by the second party, to determine a first carry value of the secret data and a first conversion parameter, and receive a fifth intermediate number sent by the second party, determine target data corresponding to the secret data according to the first carry value, the first conversion parameter and the fifth intermediate number, to determine a value range of the secret data in a shared form, and execute a secure service with the second party. The value range of the secret data can be determined through few interactions without leaking the secret data, so as to execute the secure service.

This document relates to ways of selecting digital components using secure MPC to protect user privacy and the security of data involved in each party in the selection process. In one aspect, a method includes receiving, by a first server of a secure MPC system, a digital component request from a client device. The first server identifies a selection value and a priority tier for each digital component in a set. For each tier, the first server cooperatively determines, with one or more second servers of the secure MPC system, a first secret share of a winner parameter for each digital component in the priority tier using a secure MPC process. The first server identifies that a given digital component has a highest tier of the winner parameter that indicates that the given digital component is a winning digital component.

The application relates to the technical field of data processing, and discloses a data cleaning system based on data transaction, which comprises a federal portrait and demand perception module, a privacy cleaning operator library module and a collaborative cleaning configuration module. The federal portrait and demand perception module is used for constructing a data quality portrait through federal learning and generating a quality report and a demand vector based on transaction demand. The privacy cleaning operator library module is used for providing configurable cleaning operators with built-in differential privacy mechanisms, responding to a strategy optimization module, and delivering privacy parameters. The collaborative cleaning configuration module is used for generating collaborative cleaning parameters through a secure multi-party computing protocol, so that the strategy optimization module can perfect a cleaning strategy. The multi-target strategy optimization module is used for combining the quality report, the demand vector and the collaborative parameters to generate a Pareto optimal cleaning strategy which takes into account utility, cost and privacy. The application generates a Pareto optimal strategy through a multi-target optimization model, achieves automatic strategy adaptation and multi-party safe cooperation, and improves system privacy protection, strategy optimization efficiency and collaborative efficiency.

The embodiment of the specification provides a method and device for proxy node election in secure multi-party computation, the method comprising: any data provider performing multi-round election, each round of election comprising: in a first stage, generating a random number of the party, sending encrypted data of the random number to each of other data providers, and receiving encrypted data of random numbers of each of other parties from each of other data providers; after obtaining m pieces of encrypted data, performing a second stage, sending a key of the party to each of other data providers, and receiving keys of each of other parties from each of other data providers; respectively decrypting the encrypted data of the random numbers of each of other parties by using the keys of each of other parties to obtain the random numbers of each of other parties; performing a first function operation according to an agreement by using the random number of the party and the random numbers of each of other parties to obtain a first function value; and taking a data provider corresponding to the first function value as an elected proxy node in the round. The fairness of the election can be ensured.

The invention discloses a central air conditioner AI energy-saving control system based on federated learning. The central air conditioner AI energy-saving control system comprises a data acquisition module, a federated learning framework, a control center, a monitoring module and an execution module. The data acquisition module acquires indoor data in real time and transmits the indoor data to the control center; the federated learning framework realizes model training under data privacy protection through a secure multi-party computing protocol, and performs feature extraction on multivariable time series data by adopting an energy-saving and privacy protection combined prediction model and a Transform time series prediction algorithm; and the control center generates a control instruction according to the prediction result and transmits the control instruction to a motor driver and a valve controller of the execution module, so that accurate regulation and control of the central air conditioning equipment are realized. Meanwhile, the monitoring terminal monitors the operation state of the system in real time and feeds back the operation state to the control center to ensure stable operation of the system. The user privacy is protected through federal learning, the environment change is accurately estimated by using the time sequence prediction model, the control strategy is dynamically optimized, and the energy utilization efficiency of the central air conditioner is effectively improved.

This application provides a risk warning method and apparatus based on a large model and secure multi-party computation, which can be applied to the fields of artificial intelligence, big data, and privacy computing. The method includes: collecting multimodal data with user authorization or consent, wherein the multimodal data comes from multiple data providers; performing de-identification and feature generation processing on the multimodal data to obtain multimodal feature data, wherein the de-identification and feature generation processing at least includes using secure multi-party computation to perform de-identification and feature generation processing on at least some data in the multimodal data, and the multimodal feature data includes at least two of structured data, text data, time-series data, and graph-structured data; fusing the multimodal feature data to obtain fused feature data with semantics; and processing the fused feature data using a large model to obtain a risk warning result.

The application provides a data processing method and device, computer equipment, computer readable storage medium, computer program product, and belongs to the technical field of computers. The data processing method is used for a computing node in a secure multi-party computing system, and the method comprises: obtaining target parameters and an arithmetic circuit corresponding to a target task, and data shards provided by a plurality of clients for the target task; generating an operation result shard based on the target parameters, the arithmetic circuit and the data shards, and sending the operation result shard to other computing nodes in the secure multi-party computing system; obtaining operation result shards generated by the other computing nodes, and generating a target operation result corresponding to the target task based on the locally generated operation result shard and the operation result shards generated by the other computing nodes. The technical scheme of the embodiment of the application jointly completes a computing task through a plurality of computing nodes, and takes into account computing accuracy and data privacy.

The application relates to a chain autonomous right protection method and device based on a smart contract and a dynamic data quantification model, and the method comprises the following steps: generating a transaction load and deploying the transaction load into a pre-defined data autonomous right management smart contract instance; a data demander submits a data use request to the data autonomous right management smart contract through a chain interface; the data autonomous right management smart contract receives the data use request, and matches and verifies the data use request with data authorization strategy metadata corresponding to a data asset identifier registered on the chain; a terminal user responds to a data transmission request, and performs secure calculation on local encrypted data by using a partial decryption key and a multi-party calculation hybrid protocol; and a contribution quantification algorithm pre-defined in the data autonomous right management smart contract is called to calculate a data contribution quantification value of each terminal user. The homomorphic encryption and the secure multi-party calculation are hybridized, the leakage path of data in the calculation link is cut off, and the enthusiasm of users in sharing high-quality data is stimulated.

A data processing method, device and equipment and storage medium are disclosed, which are applied to a first device. The method comprises the following steps: receiving a secure multi-party computation instruction, wherein the secure multi-party computation instruction comprises at least one target operation command and a federated dataset identifier; determining a first dataset local to the first device according to the federated dataset identifier; calling and executing a first sub-process in a task flow corresponding to each target operation command to perform secure computation on the first dataset and obtain a first sub-operation result; and combining the first sub-operation result and at least one second sub-operation result to obtain a secure multi-party computation result. The method can improve the program flow construction efficiency of secure multi-party computation.