公开(公告)号：US11443230B2

公开(公告)日：2022-09-13

申请号：US16135756

申请日：2018-09-19

Applicant: Cisco Technology, Inc.

Inventor： Nancy Cam-Winget ,  Subharthi Paul ,  Blake Anderson ,  Saman Taghavi Zargar ,  Oleg Bessonov ,  Robert Frederick Albach ,  Sanjay Kumar Agarwal ,  Mark Steven Knellinger

IPC: G06N20/00 ,  H04L9/40 ,  G06N5/04 ,  G06N20/20 ,  G06K9/62 ,  G06N7/00 ,  G06N20/10 ,  H04L67/12 ,  H04L67/00

Abstract: A trained model may be deployed to an Internet-of-Things (IOT) operational environment in order to ingest features and detect events extracted from network traffic. The model may be received and converted into a meta-language representation which is interpretable by a data plane engine. The converted model can then be deployed to the data plane and may extract features from network communications over the data plane. The extracted features may be fed to the deployed model in order to generate event classifications or device state classifications.

公开(公告)号：US12047418B2

公开(公告)日：2024-07-23

申请号：US16697362

申请日：2019-11-27

Applicant: Cisco Technology, Inc.

Inventor： Nancy Cam-Winget ,  Jianxin Wang ,  Dieter Derek Weber ,  Saman Taghavi Zargar ,  Robert Frederick Albach

IPC: H04L9/40

CPC classification number: H04L63/20 ,  H04L63/108 ,  H04L63/166

Abstract: Presented herein is a system, device and method that involve creating a policy model and policy rule structure for a policy enforcement point to support policies adapt to rapid changing external conditions in addition to traditional policies that are static. The system facilitates the use of attributes that are either or both dynamically (at run-time) created and/or defined as ephemeral. A new policy attribute may be created dynamically (at run-time). The policy attribute may be mapped as being static or ephemeral. The methodology further involves facilitating evaluation of an attribute as an atomic or programmed set of functions.

公开(公告)号：US20190236493A1

公开(公告)日：2019-08-01

申请号：US16135756

申请日：2018-09-19

Applicant: Cisco Technology, Inc.

Inventor： Nancy Cam-Winget ,  Subharthi Paul ,  Blake Anderson ,  Saman Taghavi Zargar ,  Oleg Bessonov ,  Robert Frederick Albach ,  Sanjay Kumar Agarwal ,  Mark Steven Knellinger

IPC: G06N99/00 ,  G06K9/62 ,  H04L29/06

CPC classification number: G06N20/00 ,  G06K9/6257 ,  G06K9/6267 ,  G06N5/045 ,  G06N7/005 ,  G06N20/10 ,  G06N20/20 ,  H04L63/1416 ,  H04L67/12 ,  H04L67/34

Abstract: A trained model may be deployed to an Internet-of-Things (IOT) operational environment in order to ingest features and detect events extracted from network traffic. The model may be received and converted into a meta-language representation which is interpretable by a data plane engine. The converted model can then be deployed to the data plane and may extract features from network communications over the data plane. The extracted features may be fed to the deployed model in order to generate event classifications or device state classifications.