利索-全球专利检索

  1. Login
  2. Sign Up

Search Results

33 records (took 0.02 seconds)

    VERIFICATION OF TRUSTWORTHINESS OF AGGREGATION SCHEME USED IN FEDERATED LEARNING
    1.
    发明公开
    VERIFICATION OF TRUSTWORTHINESS OF AGGREGATION SCHEME USED IN FEDERATED LEARNING 审中-公开

    公开(公告)号：US20240291633A1

    公开(公告)日：2024-08-29

    申请号：US18113219

    申请日：2023-02-23

    Applicant: International Business Machines Corporation

    Inventor： Giulio Zizzo ,  Stefano Braghin ,  Ambrish Rawat ,  Mark Purcell

    IPC: H04L9/00 ,  G06N3/098

    CPC classification number: H04L9/008 ,  G06N3/098

    Abstract: A computer-implemented method, system and computer program product for verifying the trustworthiness of an aggregation scheme utilized by an aggregator in the federated learning technique. A bit mask is received from each client used for training a machine learning algorithm using the federated learning technique. Such a bit mask contains values of ones and zeros, where a value of one indicates that the updated parameter of the global model corresponds to a parameter used by the local model trained on the client and a value of zero indicates that is not the case. These bit masks, which are encrypted, may then be combined using a homomorphic additive encryption scheme into a mask containing a matrix of values. If the mask contains a matrix of values of only the value of one, then the aggregator is deemed to be trustworthy. Otherwise, the aggregator is deemed to be untrustworthy.

    REAL-TIME RECONFIGURATION OF ADDITIVE MANUFACTURING
    4.
    发明申请
    REAL-TIME RECONFIGURATION OF ADDITIVE MANUFACTURING 有权

    公开(公告)号：US20220404819A1

    公开(公告)日：2022-12-22

    申请号：US17352959

    申请日：2021-06-21

    Applicant: International Business Machines Corporation

    Inventor： Amadou Ba ,  Ambrish Rawat ,  Joern Ploennigs

    IPC: G05B19/418 ,  B29C64/393 ,  G05B19/4099

    Abstract: A method for additive manufacturing includes identifying a discrepancy between a three-dimensional model and an object model. The three-dimensional model is a model of a three-dimensional object that is being constructed by an additive manufacturing process, and the three-dimensional object is being constructed based on the object model. The method further includes determining a reconfiguration recommendation based on the identified discrepancy. The method further includes reconfiguring the additive manufacturing process based on the reconfiguration recommendation.

    TRAINING A FEDERATED GENERATIVE ADVERSARIAL NETWORK
    5.
    发明公开
    TRAINING A FEDERATED GENERATIVE ADVERSARIAL NETWORK 审中-公开

    公开(公告)号：US20240193428A1

    公开(公告)日：2024-06-13

    申请号：US18063813

    申请日：2022-12-09

    Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION

    Inventor： Ambrish Rawat ,  Killian Levacher ,  Giulio Zizzo ,  Ngoc Minh Tran

    IPC: G06N3/088 ,  G06N3/045

    CPC classification number: G06N3/088 ,  G06N3/045

    Abstract: A method, computer system, and computer program product are provided for training a federated generative adversarial network (GAN) using private data. The method is carried out at an aggregator system having a generator and a discriminator, wherein the aggregator system is in communication with multiple participant systems each having a local feature extractor and a local discriminator. The method includes: receiving, from a feature extractor at a participant system, a set of features for input to the discriminator at the aggregator system, wherein the features include features extracted from private data that is private to the participant system; and receiving, from one or more local discriminators of the participant systems, discriminator parameter updates to update the discriminator at the aggregator system, wherein the local discriminators are trained at the participant systems.

    MACHINE LEARNING SECURITY THREAT DETECTION USING A META-LEARNING MODEL
    8.
    发明申请
    MACHINE LEARNING SECURITY THREAT DETECTION USING A META-LEARNING MODEL 有权

    公开(公告)号：US20220188690A1

    公开(公告)日：2022-06-16

    申请号：US17118648

    申请日：2020-12-11

    Applicant: International Business Machines Corporation

    Inventor： Ambrish Rawat ,  Hessel Tuinhof ,  Killian Levacher ,  Stefano Braghin

    IPC: G06N20/00 ,  G06K9/62 ,  H04L29/06

    Abstract: A computer-implemented method includes receiving at a threat detection system monitoring data in real-time from online activity in a network, the threat detection system including a machine learning model, and analyzing the monitoring data via the machine learning model to identify one or more anomalies in the monitoring data associated with a security threat to the network, the machine learning model trained to have one or more learning parameters. The method also includes receiving a subset of the monitoring data at a meta-learning module, storing the subset as time-based historical data, inputting the historical data at a meta-learning model, calculating an update policy prescribing a change to the one or more learning parameters based on the historical data, and applying the update policy to the machine learning model.

    FAIRNESS ASSESSMENT FOR DEEP GENERATIVE MODELS
    10.
    发明公开
    FAIRNESS ASSESSMENT FOR DEEP GENERATIVE MODELS 审中-公开

    公开(公告)号：US20230289573A1

    公开(公告)日：2023-09-14

    申请号：US17654093

    申请日：2022-03-09

    Applicant: International Business Machines Corporation

    Inventor： Ambrish Rawat ,  Jonathan Peter Epperlein ,  Rahul Nair ,  Killian Levacher

    IPC: G06N3/04

    CPC classification number: G06N3/0472

    Abstract: A computer-implemented method, a computer program product, and a computer system for assessing fairness of a deep generative model. A computer system receives a user defined fairness criterion for the deep generative model. A computer system probes the deep generative model to produce samples for a target output. A computer system evaluates the samples for the fairness of the deep generative model, according to the user defined fairness criterion. A computer system produces a set of recommendations for modifying the deep generative model to meet the user defined fairness criterion, in response to determining that the deep generative model does not meet the user defined fairness criterion. In response to determining that the deep generative model is to be modified, a computer system applies at least one subset of the recommendations to the deep generative model. A computer system updates the deep generative model.

Patent Agency Ranking