公开(公告)号：US11063975B2

公开(公告)日：2021-07-13

申请号：US16738583

申请日：2020-01-09

Applicant: Cisco Technology, Inc.

Inventor： Jason V. Miller ,  Adam J. O'Donnell

IPC: H04L29/06 ,  G06F21/56

Abstract: A server obtains security intelligence data used for classifying whether data associated with user activity in a network is undesirable, and classifies the data based on the security intelligence data. The server provides an initial classifying result of the data to a device associated with the data. At a subsequent time, the server obtains updated security intelligence data and re-classifies whether the first data is undesirable based on the updated security intelligence data. Responsive to a determination that the initial classifying result is changed based on the re-classifying, the server provides an updated classifying result to the device associated with the data.

公开(公告)号：US20200153848A1

公开(公告)日：2020-05-14

申请号：US16738583

申请日：2020-01-09

Applicant: Cisco Technology, Inc.

Inventor： Jason V. Miller ,  Adam J. O'Donnell

IPC: H04L29/06

Abstract: A server obtains security intelligence data used for classifying whether data associated with user activity in a network is undesirable, and classifies the data based on the security intelligence data. The server provides an initial classifying result of the data to a device associated with the data. At a subsequent time, the server obtains updated security intelligence data and re-classifies whether the first data is undesirable based on the updated security intelligence data. Responsive to a determination that the initial classifying result is changed based on the re-classifying, the server provides an updated classifying result to the device associated with the data.

公开(公告)号：US20190036949A1

公开(公告)日：2019-01-31

申请号：US15659953

申请日：2017-07-26

Applicant: Cisco Technology, Inc.

Inventor： Jason V. Miller ,  Adam J. O'Donnell

IPC: H04L29/06

Abstract: A method includes: at a server, obtaining security intelligence data used for classifying whether a data associated with a user activity in a network is undesirable at a first time; classifying whether a first data in the network is undesirable based on the security intelligence data; receiving a request for classifying whether a second data is undesirable based on the security intelligence data; determining whether the server is overloaded with tasks; if the server is determined to be overloaded with tasks: logging the second data in a repository, and tagging the second data to re-visit classification of the second data; and when the server is no longer overloaded, classifying whether the second data is undesirable to produce a second classifying result and re-classifying whether the first data is undesirable based on updated security intelligence data obtained by the server.

公开(公告)号：US20150026810A1

公开(公告)日：2015-01-22

申请号：US14505837

申请日：2014-10-03

Applicant: Cisco Technology, Inc.

Inventor： Oliver Friedrichs ,  Alfred Huger ,  Adam J. O'Donnell

IPC: H04L29/06

CPC classification number: H04L63/1416 ,  G06F21/564

Abstract: Novel methods, components, and systems for detecting malicious software in a proactive manner are presented. More specifically, we describe methods, components, and systems that leverage machine learning techniques to detect malicious software. The disclosed invention provides a significant improvement with regard to detection capabilities compared to previous approaches.

Abstract translation: 介绍了以主动的方式检测恶意软件的新方法，组件和系统。 更具体地说，我们描述利用机器学习技术来检测恶意软件的方法，组件和系统。 与先前的方法相比，所公开的发明提供了关于检测能力的显着改进。