中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

9 records (took 0.017 seconds)

    Methods and systems for peer grouping in insider threat detection
    1.
    发明授权
    Methods and systems for peer grouping in insider threat detection 有权

    公开(公告)号：US11481485B2

    公开(公告)日：2022-10-25

    申请号：US16737367

    申请日：2020-01-08

    Applicant: Visa International Service Association

    Inventor： Yuhang Wu ,  Yanhong Wu ,  Hossein Hamooni ,  Yu-San Lin ,  Hao Yang

    IPC: G06F21/00 ,  G06F21/55 ,  G06Q50/26 ,  G06F16/28 ,  G06Q10/10

    Abstract: Methods for detecting insider threats are disclosed. A method includes collecting server access data and application access data, based on the server access data and the application access data, determining nearest neighbors of an employee, and based on the nearest neighbors of the employee, determining a peer group of the employee, determining an average rank distance (ARD) of the nearest neighbors based on a ranking of the nearest neighbors in a plurality of time periods, identifying ARD gaps between the nearest neighbors, and generating scores corresponding to the ARD gaps between the nearest neighbors. One or more employees are identified that represent an internal threat to an organization based on the scores corresponding to the ARD gaps.

    System, Method, and Computer Program Product for Determining Adversarial Examples
    3.
    发明申请
    System, Method, and Computer Program Product for Determining Adversarial Examples 有权

    公开(公告)号：US20250005358A1

    公开(公告)日：2025-01-02

    申请号：US18883007

    申请日：2024-09-12

    Applicant: Visa International Service Association

    Inventor： Yuhang Wu ,  Sunpreet Singh Arora ,  Yanhong Wu ,  Hao Yang

    IPC: G06N3/08 ,  G06F18/2411 ,  G06N3/045 ,  G06N3/048

    Abstract: Provided are systems for determining adversarial examples that include at least one processor to determine a first additional input from a plurality of additional inputs based on a proximity of the first additional input to an initial input, determine a second additional input from the plurality of additional inputs based on a proximity of the second additional input to the first additional input, generate a first vector embedding, a second vector embedding and a third vector embedding based on the second additional input, generate a first relational embedding, a second relational embedding, and a third relational embedding based on the third vector embedding and the first vector embedding, concatenate the first relational embedding, the second relational embedding, and the third relational embedding to provide a concatenated version, and determine whether the first input is an adversarial example based on the concatenated version. Methods and computer program products are also provided.

    System, method, and computer program product for determining adversarial examples
    6.
    发明授权
    System, method, and computer program product for determining adversarial examples 有权

    公开(公告)号：US12124947B2

    公开(公告)日：2024-10-22

    申请号：US17106619

    申请日：2020-11-30

    Applicant: Visa International Service Association

    Inventor： Yuhang Wu ,  Sunpreet Singh Arora ,  Yanhong Wu ,  Hao Yang

    IPC: G06N3/08 ,  G06F18/2411 ,  G06N3/045 ,  G06N3/048

    CPC classification number: G06N3/08 ,  G06F18/2411 ,  G06N3/045 ,  G06N3/048

    Abstract: Provided are systems for determining adversarial examples that include at least one processor to determine a first additional input from a plurality of additional inputs based on a proximity of the first additional input to an initial input, determine a second additional input from the plurality of additional inputs based on a proximity of the second additional input to the first additional input, generate a first vector embedding, a second vector embedding and a third vector embedding based on the second additional input, generate a first relational embedding, a second relational embedding, and a third relational embedding based on the third vector embedding and the first vector embedding, concatenate the first relational embedding, the second relational embedding, and the third relational embedding to provide a concatenated version, and determine whether the first input is an adversarial example based on the concatenated version. Methods and computer program products are also provided.

    Group item recommendations for ephemeral groups based on mutual information maximization
    7.
    发明授权
    Group item recommendations for ephemeral groups based on mutual information maximization 有权

    公开(公告)号：US11443346B2

    公开(公告)日：2022-09-13

    申请号：US17070772

    申请日：2020-10-14

    Applicant: Visa International Service Association

    Inventor： Aravind Sankar ,  Yanhong Wu ,  Yuhang Wu ,  Wei Zhang ,  Hao Yang

    IPC: G06Q30/02 ,  G06N3/08 ,  G06F16/335 ,  H04L67/306

    Abstract: A computer-implemented method is disclosed for training neural networks of a group recommender to provide item recommendations for ephemeral groups having group interaction sparsity. A preference encoder and aggregator generate user and group preference embeddings from user-item interactions, wherein the preference embeddings form a latent user-group latent embedding space. The neural preference encoder and the aggregator are trained by regularizing the latent user-group embedding space to overcome the group interaction sparsity by: i) maximizing user-group mutual information (MI) between the group embeddings and the user embeddings so that the group embeddings encode shared group member preferences, while regularizing the user embeddings to capture user social associations, and ii) contextually identifying informative group members and regularizing the corresponding group embeddings using a contextually weighted user loss value to contextually weight users' personal preferences in proportion to their user-group MI to reflect personal preferences of the identified informative group members.

    System, Method, and Computer Program Product for Determining Adversarial Examples
    9.
    发明申请
    System, Method, and Computer Program Product for Determining Adversarial Examples 有权

    公开(公告)号：US20210166122A1

    公开(公告)日：2021-06-03

    申请号：US17106619

    申请日：2020-11-30

    Applicant: Visa International Service Association

    Inventor： Yuhang Wu ,  Sunpreet Singh Arora ,  Yanhong Wu ,  Hao Yang

    IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

    Abstract: Provided are systems for determining adversarial examples that include at least one processor to determine a first additional input from a plurality of additional inputs based on a proximity of the first additional input to an initial input, determine a second additional input from the plurality of additional inputs based on a proximity of the second additional input to the first additional input, generate a first vector embedding, a second vector embedding and a third vector embedding based on the second additional input, generate a first relational embedding, a second relational embedding, and a third relational embedding based on the third vector embedding and the first vector embedding, concatenate the first relational embedding, the second relational embedding, and the third relational embedding to provide a concatenated version, and determine whether the first input is an adversarial example based on the concatenated version. Methods and computer program products are also provided.

Patent Agency Ranking