利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

20 条记录 (耗时 0.02 秒)

    Preserving inter-party data privacy in global data relationships
    3.
    发明授权
    Preserving inter-party data privacy in global data relationships 有权

    公开(公告)号：US11569985B2

    公开(公告)日：2023-01-31

    申请号：US17362143

    申请日：2021-06-29

    申请人： International Business Machines Corporation

    发明人： Ngoc Minh Tran ,  Mathieu Sinn ,  Stefano Braghin

    IPC分类号： H04L9/32 ,  H04L9/08 ,  H04L9/00 ,  G06F16/28 ,  H04L9/14

    摘要： Disclosed are techniques for determining data relationships between privacy-restricted datapoints, sourced over a computer network, which require data privacy measures concealing at least some datapoints from other clients in the network that the datapoint respectively do not originate from. A first client encrypts a first datapoint with a public key of a public/private encryption scheme and communicates it to the second client along with the public key. The second client encrypts a corresponding second datapoint with the public key, then determines a relationship between the two encrypted datapoints, and communicates the determined relationship to a central client along with the public key. Random noise is encrypted by the central client and added to the determined relationship, then sent together to the first client, followed by decryption by the first client using the private key. The central client extracts the random noise after receiving the decrypted determined relationship.

    Protecting a machine learning model
    5.
    发明授权
    Protecting a machine learning model 有权

    公开(公告)号：US11036857B2

    公开(公告)日：2021-06-15

    申请号：US16192787

    申请日：2018-11-15

    申请人： International Business Machines Corporation

    发明人： Ngoc Minh Tran ,  Mathieu Sinn ,  Ambrish Rawat ,  Maria-Irina Nicolae ,  Martin Wistuba

    IPC分类号： G06F21/55 ,  G06F21/56 ,  H04L29/06 ,  G06N3/08 ,  G06F30/27

    摘要： A method for protecting a machine learning model includes: generating a first adversarial example by modifying an original input using an attack tactic, wherein the model accurately classifies the original input but does not accurately classify at least the first adversarial example; training a defender to protect the model from the first adversarial example by updating a strategy of the defender based on predictive results from classifying the first adversarial example; updating the attack tactic based on the predictive results from classifying the first adversarial example; generating a second adversarial example by modifying the original input using the updated attack tactic, wherein the trained defender does not protect the model from the second adversarial example; and training the defender to protect the model from the second adversarial example by updating the at least one strategy of the defender based on results obtained from classifying the second adversarial example.

    Federated private adversarial training
    6.
    发明授权
    Federated private adversarial training 有权

    公开(公告)号：US12118119B2

    公开(公告)日：2024-10-15

    申请号：US17110369

    申请日：2020-12-03

    申请人： International Business Machines Corporation

    发明人： Ngoc Minh Tran ,  Mathieu Sinn ,  Stefano Braghin

    IPC分类号： G06F21/62 ,  G06F18/214 ,  G06N20/00

    CPC分类号： G06F21/6245 ,  G06F18/2148 ,  G06N20/00

    摘要： One or more computer processors transmit a machine learning model and an associated loss function to a worker, wherein the worker isolates private data. The one or more computer processors receive a plurality of encrypted gradients computed utilizing the transmitted machine learning model, the associated loss function, and the isolated private data. The one or more computer processors generate a plurality of adversarial perturbations, wherein the plurality of adversarial perturbations includes true perturbations and false perturbations. The one or more computer processors obfuscate the generated plurality of adversarial perturbations. The one or more computer processors transmit the obfuscated adversarial perturbations to the worker. The one or more computer processors harden the machine learning model utilizing the transmitted obfuscated adversarial perturbations and the private data.

    TRAINING A FEDERATED GENERATIVE ADVERSARIAL NETWORK
    7.
    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

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Ambrish Rawat ,  Killian Levacher ,  Giulio Zizzo ,  Ngoc Minh Tran

    IPC分类号： G06N3/088 ,  G06N3/045

    CPC分类号： G06N3/088 ,  G06N3/045

    摘要： 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.

    TEXT DATA PROTECTION AGAINST AUTOMATED ANALYSIS
    9.
    发明申请
    TEXT DATA PROTECTION AGAINST AUTOMATED ANALYSIS 有权

    公开(公告)号：US20220164532A1

    公开(公告)日：2022-05-26

    申请号：US17101465

    申请日：2020-11-23

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Ngoc Minh Tran ,  Killian Levacher ,  Beat Buesser ,  Mathieu Sinn

    IPC分类号： G06F40/253 ,  G06N20/00 ,  G06F40/169 ,  G06F40/194 ,  G06F40/30

    摘要： A method, computer system, and a computer program product for text data protection is provided. The present invention may include receiving a text data. The present invention may also include identifying a portion of the received text data having a highest impact on a first confidence score associated with a target model prediction. The present invention may further include generating at least one semantically equivalent text relative to the identified portion of the received text data. The present invention may also include determining that the generated at least one semantically equivalent text produces a second confidence score associated with the target model prediction that is less than the first confidence score associated with the target model prediction. The present invention may further include generating a prompt to suggest modifying the identified portion of the received text data using the generated at least one semantically equivalent text.