中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

26 records (took 0.031 seconds)

    Security for generative models using attention analysis
    3.
    发明授权
    Security for generative models using attention analysis 有权

    公开(公告)号：US12292915B1

    公开(公告)日：2025-05-06

    申请号：US18527696

    申请日：2023-12-04

    Applicant: Amazon Technologies, Inc.

    Inventor： Jimit Majmudar ,  Rahul Gupta ,  Ben Smith ,  Sachin P. Joglekar

    IPC: G06F16/383 ,  G06F16/35 ,  G06F40/40

    Abstract: Devices and techniques are generally described for security threat mitigation for generative machine learning models. In some examples, first prompt data including first data associated with a first natural language input and a first span may be determined. An LLM may determine first plan data using the first prompt data. The first plan data may include a call to the first API. A first classifier model may determine a first trust score for the first span. A first attention score may be determined for the first span and the first action plan. Second plan data may be generated based on at least one of the first trust score and the first attention score or the second trust score and the second attention score.

    SYNTHETIC DATA GENERATION FOR MACHINE LEARNING MODELS
    4.
    发明申请
    SYNTHETIC DATA GENERATION FOR MACHINE LEARNING MODELS 有权

    公开(公告)号：US20240420453A1

    公开(公告)日：2024-12-19

    申请号：US18216271

    申请日：2023-06-29

    Applicant: Amazon Technologies, Inc.

    Inventor： Rahul Gupta ,  Ninareh Mehrabi ,  Palash Goyal ,  Kai-Wei Chang ,  Aram Galstyan

    IPC: G06V10/772 ,  G06F40/30 ,  G06F40/40 ,  G06V10/774

    Abstract: Techniques for generating synthetic data for machine learning (ML) models are described. A system includes a language model that processes a task and a corresponding set of example inputs to generate another input, referred to herein as a machine-generated data. The machine-generated data is processed using a ML, model (that data is being generated for) to determine a model output, and the model output is analyzed to determine whether it corresponds to a target output. If the model output corresponds to the target output, then the machine-generated data is added to the set of example inputs and one of the original example inputs is removed to generate an updated set of example inputs. The updated set can be used for various training techniques.

    Multi-device speech processing
    6.
    发明授权
    Multi-device speech processing 有权

    公开(公告)号：US11900921B1

    公开(公告)日：2024-02-13

    申请号：US17080189

    申请日：2020-10-26

    Applicant: Amazon Technologies, Inc.

    Inventor： Rahul Gupta ,  Christophe Dupuy ,  Jacob Ryan Stolee ,  Clement Chung

    IPC: G10L15/22 ,  G10L15/16

    CPC classification number: G10L15/16 ,  G10L15/22

    Abstract: Techniques for partially processing an input on a device and completing processing at a remote system are provided. The device may process an input using an on-device machine learning (ML) model, and determine to cease processing at an intermediary node of the (ML) model based on the output of the intermediary node. Based on the output of the intermediary node satisfying a condition, the device may use the output of the intermediary node to generate an output responsive to the input. Conversely, if the output of the intermediary node does not satisfy a condition, the device may send the output of the intermediary node to the remote system, so the remote system can use another machine learning model to complete processing with respect to the input.

    GENERATIVE LANGUAGE MODELS
    8.
    发明申请
    GENERATIVE LANGUAGE MODELS 有权

    公开(公告)号：US20240428783A1

    公开(公告)日：2024-12-26

    申请号：US18341412

    申请日：2023-06-26

    Applicant: Amazon Technologies, Inc.

    Inventor： Rahul Gupta ,  Charith Peris ,  Palash Goyal ,  Lisa Bauer ,  Ninareh Mehrabi

    IPC: G10L15/18 ,  G10L15/26

    Abstract: Systems and techniques for moderating responses of a generative language model are described herein. Some user inputs to a generative language model may include biases, misinformation, and other references to moderated content. To prevent the generative language model from generating responses that promote these forms of moderated content, the techniques described determine a policy corresponding to the determined moderated content category of the user input. The determined policy may correspond to a template of instructions for how the generative language model is to respond to such moderated content. The output of the generative language model may also be moderated before being presented to the user.

    MULTI-DEVICE SPEECH PROCESSING
    9.
    发明公开
    MULTI-DEVICE SPEECH PROCESSING 审中-公开

    公开(公告)号：US20240221730A1

    公开(公告)日：2024-07-04

    申请号：US18420937

    申请日：2024-01-24

    Applicant: Amazon Technologies, Inc.

    Inventor： Rahul Gupta ,  Christophe Dupuy ,  Jacob Ryan Stolee ,  Clement Chung

    IPC: G10L15/16 ,  G10L15/22

    CPC classification number: G10L15/16 ,  G10L15/22

    Abstract: Techniques for partially processing an input on a device and completing processing at a remote system are provided. The device may process an input using an on-device machine learning (ML) model, and determine to cease processing at an intermediary node of the (ML) model based on the output of the intermediary node. Based on the output of the intermediary node satisfying a condition, the device may use the output of the intermediary node to generate an output responsive to the input. Conversely, if the output of the intermediary node does not satisfy a condition, the device may send the output of the intermediary node to the remote system, so the remote system can use another machine learning model to complete processing with respect to the input.

Patent Agency Ranking