知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

50 条记录 (耗时 0.018 秒)

    SYSTEMS AND METHODS FOR QUANTIFYING DATA LEAKAGE FROM A SPLIT LAYER
    1.
    发明公开
    SYSTEMS AND METHODS FOR QUANTIFYING DATA LEAKAGE FROM A SPLIT LAYER 审中-公开

    公开(公告)号：US20230306254A1

    公开(公告)日：2023-09-28

    申请号：US17592072

    申请日：2022-02-03

    申请人： TripleBlind, Inc.

    发明人： Gharib GHARIBI ,  Andrew RADEMACHER ,  Greg STORM ,  Riddhiman DAS

    IPC分类号： G06N3/08 ,  G06N3/04

    CPC分类号： G06N3/08 ,  G06N3/04

    摘要： A system and method are disclosed for providing an artificial intelligence platform. An example method includes examining part of a global neural network to locate a split layer in the global neural network, creating an equivalent model to the part of the global neural network of a same size but having opposite operations, generating smashed data based on an operation on input data by the part of the global neural network, training the equivalent model by inputting the smashed data to generate a second a mirrored copy of the input data, quantifying a distance between the input data and the second generated set of mirrored data to yield a value and, when the value is below a threshold, determining that a current location of the split layer in the global neural network is safe for a training process.

    SYSTEMS AND METHODS FOR SECURELY TRAINING A DECISION TREE
    3.
    发明申请
    SYSTEMS AND METHODS FOR SECURELY TRAINING A DECISION TREE 有权

    公开(公告)号：US20230006980A1

    公开(公告)日：2023-01-05

    申请号：US17939797

    申请日：2022-09-07

    申请人： TripleBlind, Inc.

    发明人： Babak Poorebrahim Gilkalaye ,  Gharib GHARIBI ,  Riddhiman DAS ,  Greg STORM

    IPC分类号： H04L9/40 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06Q30/06 ,  H04L9/00 ,  H04L9/06 ,  G06Q20/40 ,  G06F17/16

    摘要： A system and method for training a decision tree are disclosed. A method includes publishing, by a first party, a first set of nominated cut-off values at a current node of a decision tree to be trained, computing a first respective impurity value for the first set of nominated cut-off values at the current node, creating first respective n shares of the first respective impurity value, transmitting, from the first party and so a second party, one of the first respective n shares of the first respective impurity value, receiving from the second party one of a second respective n shares of the second respective impurity value, adding a group of impurity values to yield a combined impurity value based on the one of the first respective n shares and the one of the second respective n shares and determining, based on the combined impurity value, a best threshold.

    Systems and methods for providing a marketplace where data and algorithms can be chosen and interact via encryption
    4.
    发明授权
    Systems and methods for providing a marketplace where data and algorithms can be chosen and interact via encryption 有权

    公开(公告)号：US11363002B2

    公开(公告)日：2022-06-14

    申请号：US16828420

    申请日：2020-03-24

    申请人： TripleBlind, Inc.

    发明人： Greg Storm ,  Riddhiman Das ,  Babak Poorebrahim Gilkalaye

    IPC分类号： G06F17/16 ,  H04L9/00 ,  H04L9/06 ,  G06Q20/40 ,  G06Q30/06 ,  H04L9/40 ,  G06Q20/12 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

    摘要： A method includes receiving, on a computer-implemented system and from user, an identification of data and an identification of an algorithm and, based on a user interaction with the computer-implemented system comprising a one-click interaction or a two-click interaction. Without further user input, the method includes dividing the data into a data first subset and a data second subset, dividing the algorithm (or a Boolean logic gate representation of the algorithm) into an algorithm first subset and an algorithm second subset, running, on the computer-implemented system at a first location, the data first subset with the algorithm first subset to yield a first partial result, running, on the computer-implemented system at a second location separate from the first location, the data second subset with the algorithm second subset to yield a second partial result and outputting a combined result based on the first partial result and the second partial result.

    SYSTEMS AND METHODS FOR PROVIDING A MARKETPLACE WHERE DATA AND ALGORITHMS CAN BE CHOSEN AND INTERACT VIA ENCRYPTION
    5.
    发明申请
    SYSTEMS AND METHODS FOR PROVIDING A MARKETPLACE WHERE DATA AND ALGORITHMS CAN BE CHOSEN AND INTERACT VIA ENCRYPTION 审中-公开

    公开(公告)号：US20200286145A1

    公开(公告)日：2020-09-10

    申请号：US16828420

    申请日：2020-03-24

    申请人： TripleBlind, Inc.

    发明人： Greg STORM ,  Riddhiman DAS ,  Babak Poorebrahim GILKALAYE

    IPC分类号： G06Q30/06 ,  G06Q20/40

    摘要： A method includes receiving, on a computer-implemented system and from user, an identification of data and an identification of an algorithm and, based on a user interaction with the computer-implemented system comprising a one-click interaction or a two-click interaction. Without further user input, the method includes dividing the data into a data first subset and a data second subset, dividing the algorithm (or a Boolean logic gate representation of the algorithm) into an algorithm first subset and an algorithm second subset, running, on the computer-implemented system at a first location, the data first subset with the algorithm first subset to yield a first partial result, running, on the computer-implemented system at a second location separate from the first location, the data second subset with the algorithm second subset to yield a second partial result and outputting a combined result based on the first partial result and the second partial result.

    PRIVACY-PRESERVING FUZZY TOKENIZATION AND ACROSS DISPARATE DATASETS
    6.
    发明公开
    PRIVACY-PRESERVING FUZZY TOKENIZATION AND ACROSS DISPARATE DATASETS 审中-公开

    公开(公告)号：US20240154792A1

    公开(公告)日：2024-05-09

    申请号：US18505003

    申请日：2023-11-08

    申请人： TripleBlind, Inc.

    发明人： Riddhiman DAS ,  Craig GENTRY

    IPC分类号： H04L9/08 ,  G06N3/043 ,  H04L9/00 ,  H04L9/32

    CPC分类号： H04L9/0833 ,  G06N3/043 ,  H04L9/008 ,  H04L9/3213

    摘要： A device may receive, at a privacy-preserving engine, first sensitive identifiers from a first dataset and second sensitive identifiers from a second dataset. A device may determine, via a fuzzy match algorithm, matches between the first sensitive identifiers and the second sensitive identifiers to yield a fuzzy match determination. A device may generate, via the fuzzy match algorithm, a set of unique identifiers in which each respective record of the first dataset and the second dataset is augmented by a respective unique identifier from the set of unique identifiers. A device may link records across the first dataset and the second dataset based on the respective unique identifier for each respective record.