中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.011 seconds)

    Private Decision Tree Evaluation Using an Arithmetic Circuit
    1.
    发明申请
    Private Decision Tree Evaluation Using an Arithmetic Circuit 有权

    公开(公告)号：US20210083841A1

    公开(公告)日：2021-03-18

    申请号：US16573827

    申请日：2019-09-17

    Applicant: SAP SE

    Inventor： Anselme Kemgne Tueno ,  Yordan Boev ,  Florian Kerschbaum

    IPC: H04L9/00 ,  G06N5/00 ,  G06N20/10 ,  G06F17/22 ,  G06F17/27

    Abstract: A non-interactive protocol is provided for evaluating machine learning models such as decision trees. A client can delegate the evaluation of a machine learning model such as a decision tree to a server by sending an encrypted input and receiving only the encryption of the result. The inputs can be encoded as vector of integers using their binary representation. The server can then evaluate the machine learning model using a homomorphic arithmetic circuit. The homomorphic arithmetic circuit provides an implementation that requires fewer multiplications than a Boolean comparison circuit. Efficient data representations are then combined with different algorithmic optimizations to keep the computational overhead and the communication cost low. Related apparatus, systems, techniques and articles are also described.

    PRIVATE DECISION TREE EVALUATION USING AN ARITHMETIC CIRCUIT
    2.
    发明公开
    PRIVATE DECISION TREE EVALUATION USING AN ARITHMETIC CIRCUIT 审中-公开

    公开(公告)号：US20230379135A1

    公开(公告)日：2023-11-23

    申请号：US18221665

    申请日：2023-07-13

    Applicant: SAP SE

    Inventor： Anselme Tueno ,  Yordan Boev ,  Florian Kerschbaum

    IPC: H04L9/00 ,  G06N20/10 ,  G06F40/126 ,  G06F40/205 ,  H04L9/06 ,  G06N5/01

    CPC classification number: H04L9/008 ,  G06N20/10 ,  G06F40/126 ,  G06F40/205 ,  H04L9/0618 ,  G06N5/01 ,  H04L2209/08

    Abstract: A non-interactive protocol is provided for evaluating machine learning models such as decision trees. A client can delegate the evaluation of a machine learning model such as a decision tree to a server by sending an encrypted input and receiving only the encryption of the result. The inputs can be encoded as vector of integers using their binary representation. The server can then evaluate the machine learning model using a homomorphic arithmetic circuit. The homomorphic arithmetic circuit provides an implementation that requires fewer multiplication than a Boolean comparison circuit. Efficient data representations are then combined with different algorithmic optimizations to keep the computational overhead and the communication cost low. Related apparatus, systems, techniques and articles are also described.

    Non-Interactive Private Decision Tree Evaluation
    6.
    发明申请
    Non-Interactive Private Decision Tree Evaluation 有权

    公开(公告)号：US20210081807A1

    公开(公告)日：2021-03-18

    申请号：US16573813

    申请日：2019-09-17

    Applicant: SAP SE

    Inventor： Anselme Kemgne Tueno ,  Yordan Boev ,  Florian Kerschbaum

    IPC: G06N5/00 ,  G06N20/00 ,  H04L9/00 ,  H04L29/06 ,  H04L9/06

    Abstract: A non-interactive protocol is provided for evaluating machine learning models such as decision trees. A client can delegate the evaluation of a machine learning model such as a decision tree to a server by sending an encrypted input and receiving only the encryption of the result. The inputs can be encoded using their binary representation. Efficient data representations are then combined with different algorithmic optimizations to keep the computational overhead and the communication cost low. Related apparatus, systems, techniques and articles are also described.

Patent Agency Ranking