公开(公告)号：US20160335353A1

公开(公告)日：2016-11-17

申请号：US15220260

申请日：2016-07-26

Applicant: Facebook, Inc.

Inventor： Nicholas Philip Gianos ,  Paul Christopher Jeffries ,  Pedram Keyani ,  Chetan Gowda ,  Siddharth Kar

IPC: G06F17/30 ,  G06F9/455

CPC classification number: G06F16/951 ,  G06F9/455 ,  G06F16/252 ,  G06F16/958

Abstract: In particular embodiments, a method comprises accessing, by one or more computing systems associated with a social-networking system, a structured document of a network application, the structured document comprising structural information and content comprising one or more embedded scripts, resources, or identifiers for the resources. The method further comprises processing the structured document to generate a model representation of the structured document, executing at least some of the content of the structured document and logging multiple snapshots of the model representation of the structured document as the model representation is generated in response to one or more interactions initiated by execution of the content. The method further comprises creating a behavior model of the network application based on the multiple snapshots of the model representation of the structured document and determining, based on the behavior model, compliance by the network application with one or more requirements of the social-networking system.

Abstract translation: 在特定实施例中，一种方法包括通过与社交网络系统相关联的一个或多个计算系统访问网络应用的结构化文档，所述结构化文档包括结构信息和包含一个或多个嵌入脚本，资源或标识符的内容 为资源。 该方法还包括处理结构化文档以生成结构化文档的模型表示，执行结构化文档的至少一些内容并记录结构化文档的模型表示的多个快照，以响应于生成模型表示 通过执行内容发起的一个或多个交互。 该方法还包括基于结构化文档的模型表示的多个快照创建网络应用的行为模型，并且基于行为模型确定网络应用与社交网络系统的一个或多个要求的一致性 。

公开(公告)号：US20140324741A1

公开(公告)日：2014-10-30

申请号：US13872811

申请日：2013-04-29

Applicant: Facebook, Inc.

Inventor： Allan Stewart ,  Eugene Zarakhovsky ,  Christopher Palow ,  Chetan Gowda ,  Brent Dorman

IPC: G06N5/02 ,  G06N99/00

CPC classification number: G06N99/005

Abstract: A method of operation of a URL spam detection system includes: identifying a feature dimension of a user action on a social networking system to detect anomalies; extracting URL chunks from a content associated with the user action; aggregating a non-content feature of the user action along the feature dimension into a URL distribution store to produce a feature distribution for each of the URL chunks; determining whether the feature distribution of a particular URL chunk within the URL chunks exceeds an expectation threshold for the feature dimension; and classifying the particular URL chunk as an illegitimate URL when the feature distribution exceeds the expectation threshold to restrict access to a particular URL chunk on a social networking system.

Abstract translation: URL垃圾邮件检测系统的操作方法包括：识别社交网络系统上的用户动作的特征维度以检测异常; 从与用户操作相关联的内容中提取URL块; 将沿着所述特征维度的所述用户动作的非内容特征聚合到URL分发存储器中，以为每个所述URL块生成特征分布; 确定所述URL块内的特定URL块的特征分布是否超过所述特征维度的期望阈值; 并且当特征分布超过期望阈值以限制对社交网络系统上的特定URL块的访问时，将特定URL块分类为非法URL。

公开(公告)号：US09378465B2

公开(公告)日：2016-06-28

申请号：US13872811

申请日：2013-04-29

Applicant: Facebook, Inc.

Inventor： Allan Stewart ,  Eugene Zarakhovsky ,  Christopher Palow ,  Chetan Gowda ,  Brent Dorman

IPC: G06N5/02 ,  G06N99/00

CPC classification number: G06N99/005

Abstract: A method of operation of a URL spam detection system includes: identifying a feature dimension of a user action on a social networking system to detect anomalies; extracting URL chunks from a content associated with the user action; aggregating a non-content feature of the user action along the feature dimension into a URL distribution store to produce a feature distribution for each of the URL chunks; determining whether the feature distribution of a particular URL chunk within the URL chunks exceeds an expectation threshold for the feature dimension; and classifying the particular URL chunk as an illegitimate URL when the feature distribution exceeds the expectation threshold to restrict access to a particular URL chunk on a social networking system.

Abstract translation: URL垃圾邮件检测系统的操作方法包括：识别社交网络系统上的用户动作的特征维度以检测异常; 从与用户操作相关联的内容中提取URL块; 将沿着所述特征维度的所述用户动作的非内容特征聚合到URL分发存储器中，以为每个所述URL块生成特征分布; 确定所述URL块内的特定URL块的特征分布是否超过所述特征维度的期望阈值; 并且当特征分布超过期望阈值以限制对社交网络系统上的特定URL块的访问时，将特定URL块分类为非法URL。