MACHINE-LEARNING TECHNIQUES FOR DETECTION OF UNAUTHORIZED ACCESS OF INTERACTIVE COMPUTING ENVIRONMENT FUNCTIONS

    公开(公告)号:US20230283628A1

    公开(公告)日:2023-09-07

    申请号:US18040627

    申请日:2021-08-04

    Applicant: KOUNT INC.

    CPC classification number: H04L63/1433 H04L63/1416 H04L41/16

    Abstract: An online security analysis system determines a categorical value in an online activity and also determines conversion factors that are associated with the categorical value. Based on the conversion factors, the online security analysis system identifies at least one aggregated value for a numerical feature that is associated with previous online activities for the categorical value. In addition, the online security analysis system generates an embedding vector that describes the aggregated value associated with the categorical value. The embedding vector is provided to an online activity analysis model that is trained to generate prediction data for the online activity, based on the aggregated values associated with the categorical value. The prediction data is transmitted to an online system for use in controlling access of a client device to a function of the online system.

    Fast component enumeration in graphs with implicit edges

    公开(公告)号:US11176200B2

    公开(公告)日:2021-11-16

    申请号:US16822450

    申请日:2020-03-18

    Applicant: Kount Inc.

    Abstract: A method and system for graphical enumeration. The method includes creating an ordered set of vertices for a graph such that each vertex is associated with a corresponding index, and wherein each vertex in the ordered set of vertices includes information. A plurality of keys is created for defining the information. A plurality of lists of vertices is created, each of which is associated with a corresponding key such that vertices in a corresponding list include information associated with the corresponding key. For a first list of vertices, a least valued index is determined from a group of associated vertices based on vertices in the first list and vertices pointed to by the vertices in the first list. Also, all associated vertices are pointed to a root vertex associated with the least valued index.

    AUTHENTICATING USERS FOR ACCURATE ONLINE AUDIENCE MEASUREMENT
    24.
    发明申请
    AUTHENTICATING USERS FOR ACCURATE ONLINE AUDIENCE MEASUREMENT 审中-公开
    认证用户准确的在线访问测量

    公开(公告)号:US20160335662A1

    公开(公告)日:2016-11-17

    申请号:US15223736

    申请日:2016-07-29

    Applicant: Kount Inc.

    CPC classification number: G06Q30/0248 G06Q30/0242 G06Q30/0246 G06Q30/0609

    Abstract: Online entities oftentimes desire to ascertain information about their audience members. To determine information about audience members and their activities, online transactions including information about transactions performed by audience members are collected. One or more audience analysis processes are applied to the online transactions to determine the collection of online transactions performed by a given audience member. With an accurate assignment of online transaction to the audience member, the audience member and associated transactions may be classified as a legitimate or illegitimate.

    Abstract translation: 在线实体通常希望确定有关观众信息的信息。 为了确定有关观众成员及其活动的信息,收集包括观众成员进行的交易信息的在线交易。 将一个或多个受众分析流程应用于在线交易,以确定由给定受众成员执行的在线交易的收集。 将在线交易准确分配给观众,观众和相关交易可能被归类为合法或非法。

    Fast Component Enumeration in Graphs with Implicit Edges
    27.
    发明申请
    Fast Component Enumeration in Graphs with Implicit Edges 有权
    具有隐式边的图中的快速组件枚举

    公开(公告)号:US20150294027A1

    公开(公告)日:2015-10-15

    申请号:US14728499

    申请日:2015-06-02

    Applicant: Kount Inc.

    CPC classification number: G06T11/206 G06T11/20 G06T11/203

    Abstract: A method and system for graphical enumeration. The method includes creating an ordered set of vertices for a graph such that each vertex is associated with a corresponding index, and wherein each vertex in the ordered set of vertices includes information. A plurality of keys is created for defining the information. A plurality of lists of vertices is created, each of which is associated with a corresponding key such that vertices in a corresponding list include information associated with the corresponding key. For a first list of vertices, a least valued index is determined from a group of associated vertices based on vertices in the first list and vertices pointed to by the vertices in the first list. Also, all associated vertices are pointed to a root vertex associated with the least valued index.

    Abstract translation: 一种用于图形化枚举的方法和系统。 该方法包括为图形创建有序的顶点集合,使得每个顶点与相应的索引相关联,并且其中顶点的有序集合中的每个顶点包括信息。 创建多个键来定义信息。 创建多个顶点列表,每个列表与对应的密钥相关联,使得相应列表中的顶点包括与对应密钥相关联的信息。 对于顶点的第一列表,基于第一列表中的顶点和由第一列表中的顶点指向的顶点,从一组相关联的顶点确定最小值索引。 此外,所有相关的顶点都指向与最小值索引相关联的根顶点。

    Online Machine Data Collection And Archiving Process
    28.
    发明申请
    Online Machine Data Collection And Archiving Process 审中-公开
    在线机器数据收集和归档过程

    公开(公告)号:US20150193769A1

    公开(公告)日:2015-07-09

    申请号:US14664200

    申请日:2015-03-20

    Applicant: Kount Inc.

    Abstract: An online machine data collection and archiving process generates a machine data profile of a customer computer accessing a transaction form of a merchant web site and links the machine data profile and a transaction record with customer identifying information using a unique transaction identification string. The process preferably captures parameters typically communicated as a part of web accesses, such as an IP address, an HTTP header, and cookie information. The process additionally causes the customer computer to process self-identification routines by processing coding within the merchant transaction form, the self-identification routines yielding further profile parameters. The process further includes a routine for bypassing an intervening proxy to the merchant web site to reveal the true IP address of the customer computer.

    Abstract translation: 在线机器数据收集和归档过程生成访问商家网站的交易形式的客户计算机的机器数据简档,并使用唯一的交易标识串将机器数据简档和交易记录与客户识别信息相链接。 该过程优选地捕获通常作为web访问的一部分传送的参数,诸如IP地址,HTTP头和cookie信息。 该过程另外使得客户计算机通过处理商家交易形式内的编码来处理自身识别例程,该自我标识例程产生其他简档参数。 该过程还包括用于绕过中间代理到商户网站以显示客户计算机的真实IP地址的例程。

    TECHNIQUES FOR DETERMINING LEGITIMACY OF EMAIL ADDRESSES FOR ONLINE ACCESS CONTROL

    公开(公告)号:US20240250981A1

    公开(公告)日:2024-07-25

    申请号:US18597551

    申请日:2024-03-06

    Applicant: KOUNT, INC.

    CPC classification number: H04L63/1433 H04L63/126

    Abstract: Various aspects involve determining legitimacy of an email address for risk assessment or other purposes. For instance, a risk assessment computing system receives a risk assessment query that identifies an email address. The risk assessment computing system determines a set of features for the email address. For each feature, the risk assessment computing system calculates an illegitimacy score by calculating a deviation of the feature from an expected safe value for the feature that is determined from historical email addresses. The risk assessment computing system aggregates the illegitimacy scores of the plurality of features into an aggregated illegitimacy score and further transmits a legitimacy risk value to a remote computing system. The legitimacy risk value indicates the aggregated illegitimacy score and can be used in controlling access of a computing device associated with the email address to one or more interactive computing environments.

    Dynamic service worker code for storing information in web browser

    公开(公告)号:US11675868B2

    公开(公告)日:2023-06-13

    申请号:US17391749

    申请日:2021-08-02

    Applicant: KOUNT INC.

    CPC classification number: G06F16/9577 G06F8/51 G06F8/71 G06F16/9535

    Abstract: Systems and methods for storing information in a web browser by dynamically generating service worker codes are provided. In one example, an online system receives a request from a client device to store data included in the request in a service worker code. The online system modifies a source code of a particular service worker code to include the data to be stored and transmits the modified service worker code to the client device. The client device receives and stores the modified service worker code embedded with the data. The client device receives a request for a particular data associated with a web page and determines that the modified service worker code contains the requested particular data. The client device retrieves the requested particular data from the modified service worker code and updates the web page with the retrieved particular data.

Patent Agency Ranking