中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.011 seconds)

    SYSTEMS AND METHODS FOR GENERATING AND APPLYING A SECURE STATISTICAL CLASSIFIER
    1.
    发明申请
    SYSTEMS AND METHODS FOR GENERATING AND APPLYING A SECURE STATISTICAL CLASSIFIER 有权

    公开(公告)号：US20220188706A1

    公开(公告)日：2022-06-16

    申请号：US17683395

    申请日：2022-03-01

    Applicant: NEC Corporation Of America ,  Bar-Ilan University ,  NEC Corporation

    Inventor： Jun FURUKAWA ,  Joseph KESHET ,  Kazuma OHARA ,  Toshinori ARAKI ,  Hikaru TSUCHIDA ,  Takuma AMADA ,  Kazuya KAKIZAKI ,  Shir AVIV-REUVEN

    IPC: G06N20/00 ,  G06N5/04

    Abstract: There is provided a system for computing a secure statistical classifier, comprising: at least one hardware processor executing a code for: accessing code instructions of an untrained statistical classifier, accessing a training dataset, accessing a plurality of cryptographic keys, creating a plurality of instances of the untrained statistical classifier, creating a plurality of trained sub-classifiers by training each of the plurality of instances of the untrained statistical classifier by iteratively adjusting adjustable classification parameters of the respective instance of the untrained statistical classifier according to a portion of the training data serving as input and a corresponding ground truth label, and at least one unique cryptographic key of the plurality of cryptographic keys, wherein the adjustable classification parameters of each trained sub-classifier have unique values computed according to corresponding at least one unique cryptographic key, and providing the statistical classifier, wherein the statistical classifier includes the plurality of trained sub-classifiers.

    SYSTEMS AND METHODS FOR GENERATING AND APPLYING A SECURE STATISTICAL CLASSIFIER
    2.
    发明申请
    SYSTEMS AND METHODS FOR GENERATING AND APPLYING A SECURE STATISTICAL CLASSIFIER 审中-公开

    公开(公告)号：US20200293944A1

    公开(公告)日：2020-09-17

    申请号：US16353046

    申请日：2019-03-14

    Applicant: NEC Corporation Of America ,  Bar-Ilan University ,  NEC Corporation

    Inventor： Jun FURUKAWA ,  Joseph KESHET ,  Kazuma OHARA ,  Toshinori ARAKI ,  Hikaru TSUCHIDA ,  Takuma AMADA ,  Kazuya KAKIZAKI ,  Shir AVIV-REUVEN

    IPC: G06N20/00 ,  G06N5/04

    Abstract: There is provided a system for computing a secure statistical classifier, comprising: at least one hardware processor executing a code for: accessing code instructions of an untrained statistical classifier, accessing a training dataset, accessing a plurality of cryptographic keys, creating a plurality of instances of the untrained statistical classifier, creating a plurality of trained sub-classifiers by training each of the plurality of instances of the untrained statistical classifier by iteratively adjusting adjustable classification parameters of the respective instance of the untrained statistical classifier according to a portion of the training data serving as input and a corresponding ground truth label, and at least one unique cryptographic key of the plurality of cryptographic keys, wherein the adjustable classification parameters of each trained sub-classifier have unique values computed according to corresponding at least one unique cryptographic key, and providing the statistical classifier, wherein the statistical classifier includes the plurality of trained sub-classifiers.

    SECURE COMPUTATION SERVER, TRAIL MANAGEMENT METHOD, AND PROGRAM
    3.
    发明申请
    SECURE COMPUTATION SERVER, TRAIL MANAGEMENT METHOD, AND PROGRAM 有权

    公开(公告)号：US20220261507A1

    公开(公告)日：2022-08-18

    申请号：US17628953

    申请日：2019-07-24

    Applicant: NEC Corporation

    Inventor： Hikaru TSUCHIDA ,  Kazuma OHARA ,  Toshinori ARAKI ,  Takuma AMADA

    IPC: G06F21/64 ,  H04L9/00 ,  H04L9/08

    Abstract: A secure computation server includes: a computation processing part that performs secure computation by using data x received from a client and computes a computation result R; and a trail registration part that makes a predetermined trail storage system to store first trail data for certifying identity of the data x, the first trail data having been calculated from the data x, and second trail data for certifying a relationship between the data x and the computation result R. The predetermined trail storage system manages the first and second trail data in a non-rewritable manner and provides the first and second trail data to a predetermined audit node.

    INFORMATION PROCESSING APPARATUS, SECURE COMPUTATION METHOD, AND PROGRAM
    4.
    发明申请
    INFORMATION PROCESSING APPARATUS, SECURE COMPUTATION METHOD, AND PROGRAM 有权

    公开(公告)号：US20220129567A1

    公开(公告)日：2022-04-28

    申请号：US17429780

    申请日：2019-02-12

    Applicant: NEC Corporation

    Inventor： Hikaru TSUCHIDA ,  Toshinori ARAKI ,  Kazuma OHARA ,  Takuma AMADA

    IPC: G06F21/60 ,  G06F21/31 ,  G06F7/58 ,  G06F7/76

    Abstract: There is provided an information processing apparatus that executes efficient type conversion processing in four-party computation using 2-out-of-4 replicated secret sharing. The information processing apparatus comprises a basic operation seed storage part, a reshare value computation part, and a share construction part. The basic operation seed storage part stores a seed for generating a random number used when computation is performed on a share. The reshare value computation part generates a random number using the seed, computes a share reshare value using the generated random number, and transmits data regarding the generated random number to other apparatuses. The share construction part constructs a share for type conversion using the data regarding the generated random number and the share reshare value received from other apparatuses.

    LEARNING DEVICE, FEATURE CALCULATION PROGRAM GENERATION METHOD AND SIMILARITY CALCULATOR
    5.
    发明公开
    LEARNING DEVICE, FEATURE CALCULATION PROGRAM GENERATION METHOD AND SIMILARITY CALCULATOR 审中-公开

    公开(公告)号：US20230259818A1

    公开(公告)日：2023-08-17

    申请号：US18014099

    申请日：2020-07-06

    Applicant: NEC Corporation

    Inventor： Takuma AMADA ,  Kazuya KAKIZAKI

    IPC: G06N20/00 ,  G06F21/32

    CPC classification number: G06N20/00 ,  G06F21/32

    Abstract: Calculate a plurality of feature vectors representing features of an input sample from the input sample which is multidimensional data by using a plurality of feature calculation models. Calculate similarity between an average value of the plurality of feature vectors and a representative vector corresponding to a class to which the input sample belongs among a plurality of representative vectors corresponding to a plurality of classes respectively, the representative vector having same dimensionality as each of the plurality of feature vectors. Learn parameters of the plurality of feature calculation models based on an evaluation function in which a value is larger as the similarity between the average value of the plurality of feature vectors and the representative vector corresponding to the class to which the input sample belongs is smaller.

    ROBUST LEARNING DEVICE, ROBUST LEARNING METHOD, PROGRAM, AND STORAGE DEVICE
    7.
    发明申请
    ROBUST LEARNING DEVICE, ROBUST LEARNING METHOD, PROGRAM, AND STORAGE DEVICE 有权

    公开(公告)号：US20220335298A1

    公开(公告)日：2022-10-20

    申请号：US17764316

    申请日：2019-10-01

    Applicant: NEC Corporation

    Inventor： Takuma AMADA ,  Kazuya KAKIZAKI ,  Toshinori ARAKI

    IPC: G06N3/08 ,  G06N3/04

    Abstract: A robust learning device is a learning device that, with a parameter of n neural networks, training data, and a correct label serving as inputs, outputs the updated parameter, including: a model selection unit that selects neural networks, which are less than n and equal to or more than two, among the n neural networks; a limited objective function calculation unit that calculates, in a calculation process of an objective function including a process in which a value of the objective function becomes smaller as an output of the neural networks to the training data is closer to the correct label and a degree of similarity between the neural networks is smaller, a limited objective function including only the process relating to the neural networks selected by the model selection unit; and an update unit that updates the parameter such that a value of the limited objective function is decreased.

    LEARNING DEVICE, LEARNING METHOD, AND RECORDING MEDIUM
    9.
    发明公开
    LEARNING DEVICE, LEARNING METHOD, AND RECORDING MEDIUM 审中-公开

    公开(公告)号：US20230252284A1

    公开(公告)日：2023-08-10

    申请号：US18012752

    申请日：2020-06-30

    Applicant: NEC Corporation

    Inventor： Takuma AMADA

    IPC: G06N3/08 ,  G06N3/045

    CPC classification number: G06N3/08 ,  G06N3/045

    Abstract: A learning device includes: an incorrect answer prediction calculation unit which obtains incorrect answer class prediction probability vectors by excluding a correct answer class element from prediction probability vectors of neural network models for supervised learning data; and an updating unit which performs learning of two of the neural network models so as to further reduce a value of an objective function which includes a diversity function, a value of diversity function decreasing as an angle between the incorrect answer class prediction probability vectors of the two neural network models increases.

    ADVERSARIAL EXAMPLE DETECTION DEVICE, ADVERSARIAL EXAMPLE DETECTION METHOD, AND PROGRAM
    10.
    发明公开
    ADVERSARIAL EXAMPLE DETECTION DEVICE, ADVERSARIAL EXAMPLE DETECTION METHOD, AND PROGRAM 审中-公开

    公开(公告)号：US20230222782A1

    公开(公告)日：2023-07-13

    申请号：US18007521

    申请日：2020-06-05

    Applicant: NEC Corporation

    Inventor： Takuma AMADA ,  Kazuya KAKIZAKI ,  Toshinori ARAKI

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: An adversarial example detection device includes a first feature extraction unit configured to extract first features with respect to input data and comparative data in a first calculation method, a second feature extraction unit configured to extract second features with respect to the input data and the comparative data in a second calculation method different from the first calculation method, and a determination unit configured to determine whether or not at least one piece of the input data and the comparative data is an adversarial example through calculation using the first features and the second features.

Patent Agency Ranking