Embodiments of the present disclosure provide methods and apparatuses for blockchain-based multi-party computation, a device and a medium, relate to blockchain technology in the field of computer technology. An embodiment of the method can include: encrypting business data, to obtain a ciphertext of the business data; hashing the ciphertext of the business data, to obtain a hash result of the business data; sending the hash result of the business data to a blockchain node, so that the blockchain node writes the hash result of the business data into a blockchain; and sending the ciphertext of the business data to a target trusted computing module in a target server, for instructing the target trusted computing module to perform multi-party computation based on the ciphertext of the business data and the hash result of the business data in the blockchain.

Embodiments of the present disclosure provide hierarchical, differential privacy enhancements to federated, machine learning. Local machine learning models may be generated and/or trained by data owners participating in the federated learning framework based on their respective data sets. Noise corresponding to and satisfying a first privacy loss requirement are introduced to the data owners' respective data sets, and noise corresponding to and satisfying a first privacy loss requirement are introduced to the local models generated and/or trained by the data owners. The data owners transmit model data corresponding to their respective local models to a coordinator, which in turn aggregates the data owners' model data. After introducing noise corresponding to and satisfying a third privacy loss requirement to the aggregated model data, the coordinator transmits the aggregated model data to the data owners to facilitate updating and/or re-training on their respective machine learning models.

A method includes obtaining, from a server, a filter including a set of encrypted identifiers each encrypted with a server key controlled by the server. The method includes obtaining a request that requests determination of whether a query identifier is a member of a set of identifiers corresponding to the set of encrypted identifiers. The method also includes transmitting an encryption request to the server that requests the server to encrypt the query identifier. The method includes receiving, from the server, an encrypted query identifier including the query identifier encrypted by the server key and determining, using the filter, whether the encrypted query identifier is not a member of the set of encrypted identifiers. When the encrypted query identifier is not a member of the set of encrypted identifiers, the method includes reporting that the query identifier is not a member of the set of identifiers.

Methods and systems are presented for providing a multi-party computation (MPC) framework for dynamically configuring, deploying, and utilizing an MPC system for performing distributed computations. Based on device attributes and network attributes associated with computer nodes that are available to be part of the MPC system, a configuration for the MPC system is determined. The configuration may specify a total number of computer nodes within the MPC system, a minimum number of computer nodes required to participate in performing a computation process, a key distribution mechanism, and a computation processing mechanism. Encryption keys are generated and distributed among the computer nodes based on the key distribution mechanism. Upon receiving a request for performing the computation, updated network attributes are obtained. The configuration of the MPC system is dynamically modified based on the updated network attributes, and the MPC system performs the computations according to the modified configuration.

Implementations of this specification provide query optimization methods, apparatuses, and systems for secure multi-party databases. In an implementation, a method includes: receiving a current query associated with a plurality of target database of a multi-party database system, generating a plurality of execution plans for the current query, determining, for each execution plan, a respective cost computation formula of a plurality of cost computation values for computing an execution cost of jointly executing the execution plan by the plurality of target databases, receiving a secure computation result from each of a plurality of query engines corresponding to the plurality of target databases, and determining an optimal execution plan having a lowest cost value in the plurality of cost computation formulas based on the secure computation result.

A computer-implemented method for providing a distributed data processing service for performing a secure multiparty computation of a function on at least first and second items of private input data using at least a first and a second computing engine communicatively coupled via a communication network.

Provided are methods and systems for performing a secure machine learning analysis over an instance of data. An example method includes acquiring, by a client, a homomorphic encryption scheme, and at least one machine learning model data structure. The method further includes generating, using the encryption scheme, at least one homomorphically encrypted data structure, and sending the encrypted data structure to at least one server. The method includes executing a machine learning model, by the at least one server based on the encrypted data structure to obtain an encrypted result. The method further includes sending, by the server, the encrypted result to the client where the encrypted result is decrypted. The machine learning model includes neural networks and decision trees.

A computer-implement method comprises: selecting a trusted computing node via smart contract on a blockchain; completing remote attestation of the selected trusted computing node; writing secret information to an enclave of the selected node; causing a thin device to establish a private connection with the selected node without revealing the secret information; and causing the selected node to act as a proxy on the blockchain for the device. Another method comprises: receiving a signed device access request from a device owner; validating, by the verification node, the received request; executing, by a verification node, a smart contract on a blockchain based on the received request; and producing, based on the executed smart contract, an output command to access the device for the device to validate, decrypt and execute.

A system for using biometric data to authenticate a subject as an individual whose biometric data has been previously obtained. A second transducer has a digital electronic signal output characterizing a biometric of the subject; a second computing facility to receive the digital electronic signal; and an array of servers. These components implement processes including causing generating of shards from the digital electronic signal and distributing of the generated shards to the array of servers; causing storing of the generated shards and performing of a data exchange process using a subset of the generated shards to develop information relating to authentication of the subject; and causing processing of the authentication information in a verification process to indicate whether the subject is authenticated as the individual. A related enrollment system is also provided.

A method includes dividing a plurality of filters in a first layer of a neural network into a first set of filters and a second set of filters, applying each of the first set of filters to an input of the neural network, aggregating, at a second layer of the neural network, a respective one of a first set of outputs with a respective one of a second set of outputs, splitting respective weights of specific neurons activated in each remaining layer, at each specific neuron from each remaining layer, applying a respective filter associated with each specific neuron and a first corresponding weight, obtaining a second set of neuron outputs, for each specific neuron, aggregating one of the first set of neuron outputs with one of a second set of neuron outputs and generating an output of the neural network based on the aggregated neuron outputs.