BIOMETRIC EXTRACTION METHOD AND DEVICE FOR SECURE MULTI-PARTY COMPUTATION SYSTEM

    公开(公告)号:US20240427867A1

    公开(公告)日:2024-12-26

    申请号:US18705116

    申请日:2022-10-13

    Abstract: A biometric feature extraction method for a secure multi-party computation system. The method comprises: acquiring preprocessed fragments of a biometric feature; and performing feature extraction on the preprocessed fragments using a neural network, wherein in the first N convolutional and pooling layers, performing data computation on the preprocessed fragments by means of secure multi-party computation respectively to obtain intermediate data; and in the convolutional and pooling layers subsequent to the Nth layer, aggregating the intermediate data to a single-party server platform for subsequent computation, and inputting the same to a fully connected layer for completing feature extraction. There also relates to a biometric feature extraction device for a secure multi-party computation system, a computer storage medium and a computer program product.

    Interconnected region controller, interconnected region control method, and computer storage medium

    公开(公告)号:US11343168B2

    公开(公告)日:2022-05-24

    申请号:US16641006

    申请日:2018-08-27

    Abstract: The present disclosure provides a region interconnect (RI) controller including a region interconnect routing module configured when a tenant is created. The region interconnect routing module is configured to assign a first identifier to the tenant for identifying traffic of the tenant, in a core switching network, create a virtual routing forwarding instance for the tenant and bind the first identifier and the virtual routing forwarding instance, and to activate a dynamic routing protocol in the core switching network and bind a dynamic routing protocol instance to the virtual routing forwarding instance, where virtual routers corresponding to the tenant and distributed in a plurality of independent network partitions are associated with the region interconnect control method and a computer storage medium. The technical solution of the present disclosure achieves a direct intranet connection in a heterogeneous SDN network region.

    DISTRIBUTED GRAPH EMBEDDING-BASED FEDERATED GRAPH CLUSTERING METHOD, APPARATUS, AND READABLE STORAGE MEDIUM

    公开(公告)号:US20250148011A1

    公开(公告)日:2025-05-08

    申请号:US18833611

    申请日:2022-09-07

    Abstract: Provided are a federated graph clustering method based on distributed graph embedding, a device, and a readable storage medium. The method comprises: constructing a first graph on the basis of first party data, and constructing a second graph on the basis of second party data; performing an encrypted intersection on the first party data and the second party data, determining common nodes in the first graph and the second graph, and associating the first graph with the second graph according to the common nodes to obtain a federated graph; learning on the federated graph by using a random walk-based distributed graph embedding algorithm, and determining a first graph embedding vector [PiA, PiB] starting from the first graph and a second graph embedding vector [PiA′, PiB′] starting from the second graph; and performing a clustering analysis on the first graph embedding vector [PiA, PiB] and the second graph embedding vector [PiA′, PiB′] of the federated graph on the basis of a federated clustering method to obtain a clustering result. By utilizing the present method, federated graph clustering can be carried out on private data of two parties, and a better clustering effect is obtained.

    Data processing method and apparatus

    公开(公告)号:US11374878B2

    公开(公告)日:2022-06-28

    申请号:US17279413

    申请日:2019-10-22

    Abstract: The present disclosure provides a method and a device for data processing. The method includes acquiring at least two pathways of communication messages, where the at least two pathways of communication messages are messages intercepted in a bypass manner from messages transmitted by a service processing system to an external system; and the service processing system does not execute logic of record storage; processing the at least two pathways of communication messages, and determining communication messages to-be-stored from the at least two pathways of communication messages processed; and according to the at least two pathways of communication messages, storing the communication messages to-be-stored in a database.

    SDN-based packet mirroring method, and network traffic monitoring and management system

    公开(公告)号:US11088965B2

    公开(公告)日:2021-08-10

    申请号:US16474970

    申请日:2017-12-21

    Abstract: The present disclosure relates to a SDN-based method for mirroring packets, wherein a SDN controller is coupled to an upper layer application and at least one data switching exchange respectively, and the method including: a) the upper layer application sends a mirroring instruction to the SDN controller through a first northbound interface of the SDN controller; b) the SDN controller generates a second flow table based on the mirroring instruction and a first flow table sent by a first data switching exchange; wherein the first data switching exchange initiates transmission of the packets, the first flow table encapsulates the packets, and the second flow table includes at least an action command corresponding to the mirroring instruction; and c) a second data switching exchange extracts the packets from the second flow table, and mirrors the packets to the designated node based on the action command.

    Network device driver file generating system, method, device, and medium

    公开(公告)号:US20250004787A1

    公开(公告)日:2025-01-02

    申请号:US18723660

    申请日:2022-08-10

    Abstract: The present disclosure relates to a network operation and maintenance technology, and in particular to a system and method for generating network device driver files. One aspect of the present disclosure provides a system for generating network device driver files. The system includes: a network device capability model construction unit, configured to construct a capability model following a standard format on the basis of a capability set acquired from a network device; a driver function interface generation unit, configured to generate, based on the capability model, a driver function interface that can be called by an upper-layer application; and a control message generation unit, configured to receive configuration data from the upper-layer application via the generated driver function interface, and to generate, based on the configuration data, a control message for driving the network device.

    Method and device for communication between microservices

    公开(公告)号:US11683316B2

    公开(公告)日:2023-06-20

    申请号:US17596420

    申请日:2020-07-17

    CPC classification number: H04L63/101 H04L63/20 H04L67/10 H04L9/40 H04L63/10

    Abstract: A method for communication between microservices, performed by a first host machine node, includes: obtaining a first microservice instance located on the first host machine node, determining a first microservice to which the first microservice instance belongs, and determining a list of triples corresponding to the first microservice according to the first microservice. The list of triples corresponding to the first microservice includes at least one triple, each triple of the at least one triple includes a visitor of the microservice, a visited party of the microservice, and an access port, and the visitor of the microservice of each triple included in the list of triples corresponding to the first microservice is the first microservice. The method also includes determining, by the first host machine node, an access policy of the first microservice instance according to the list of triples corresponding to the first microservice.

Patent Agency Ranking