利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

326 条记录 (耗时 0.027 秒)

    SYSTEM FOR AUTOMATED MODEL SELECTION TO FACILITATE DETECTION OF SUSPICIOUS DIGITAL IDENTIFIERS
    2.
    发明公开
    SYSTEM FOR AUTOMATED MODEL SELECTION TO FACILITATE DETECTION OF SUSPICIOUS DIGITAL IDENTIFIERS 审中-公开

    公开(公告)号：US20240338576A1

    公开(公告)日：2024-10-10

    申请号：US18471099

    申请日：2023-09-20

    申请人： Lookout, Inc.

    发明人： Aungon Nag Radon

    IPC分类号： G06N3/0985 ,  H04L41/16

    CPC分类号： G06N3/0985 ,  H04L41/16

    摘要： A system for providing automated model generation to facilitate automated detection of suspicious digital identifiers is disclosed. The system trains, during a training process, a plurality of trainable machine learning models using a labeled dataset containing data verified as suspicious or non-suspicious to generate a plurality of trained machine learning models based on candidate machine learning algorithms. The system generates an optimal machine learning model from the plurality of trainable machine learning models. The optimal machine learning model can have an optimal combination of hyperparameters and an optimal model parameter combination learned via the training process using the optimal hyperparameter combination. The optimal machine learning model has a highest performance for suspiciousness determination according to a performance metric when compared to other trained machine learning models. The system can receive a request to determine whether an identifier is suspicious and utilizes the optimal machine learning model to perform the determination.

    Phishing protection using cloning detection
    9.
    发明授权
    Phishing protection using cloning detection 有权

    公开(公告)号：US11356478B2

    公开(公告)日：2022-06-07

    申请号：US16688925

    申请日：2019-11-19

    申请人： Lookout, Inc.

    发明人： Jeremy Boyd Richards ,  Brian James Buck

    IPC分类号： H04L9/40 ,  H04L67/02

    摘要： Techniques for phishing protection using cloning detection are described herein. The techniques described herein can include a server which hosts a website detecting that a fetcher is a cloning toolkit or an entity known for using a cloning toolkit. The techniques can also include a server which hosts a downloadable application (such as a mobile application) detecting that a fetcher for the application is a cloning toolkit or an entity known for using a cloning toolkit. The detection can be done in several ways, such as by analyzing data logs for patterns associated with cloning toolkits or entities known for using cloning toolkits. The techniques described herein can also include a part of an end user device (such as a part of a mobile device) detecting a clone (such as a clone website or application) that was cloned by a cloning toolkit. Then, upon detection, security actions can be taken.