Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Cognitive Recognition Engine for Modern Day Applications

IP.com Disclosure Number: IPCOM000248065D
Publication Date: 2016-Oct-21
Document File: 1 page(s) / 67K

Publishing Venue

The IP.com Prior Art Database

Abstract

Currently available application detection engines come with a predefined set of in-built signatures for well-known applications that can be recognized. Application recognition engines provide options to create custom apps for unrecognized applications. To create custom applications, the administrator has to analyze the network traffic corresponding to the custom-app to be created and come up with a signature, which is a time consuming and tedious task. Future updates of the signature would require manual intervention to update the existing custom application's matching criteria by the administrator.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 91% of the total text.

Page 01 of 1

Cognitive Recognition Engine for Modern Day Applications

     Currently available application detection engines come with a predefined set of in-built signatures for well-known applications that can be recognized. Application recognition engines provide options to create custom apps for unrecognized applications. To create custom applications, the administrator has to analyze the network traffic corresponding to the custom-app to be created and come up with a signature, which is a time consuming and tedious task. Future updates of the signature would require manual intervention to update the existing custom application's matching criteria by the administrator.

     Creating the signatures for unrecognized applications is cognitive and automatic in nature with zero manual intervention. An application which is not recognized by the detection engine and being accessed in the network over a period of time would be analyzed and a custom-signature created automatically without putting the onus on the user to analyze the metadata and come-up with a signature.

     Application detection engines also provide metadata in the form of hostname, URL, server certificate details including common name, organization name, hit count. These metadata parameters are directed to a database in analytics server where a regexp generator will be churning out top-X patterns based on the hit counts periodically. The analytic servers create new signatures based on the patterns. These newly created signatu...