US 11,736,364 B2
Cascade-based classification of network devices using multi-scale bags of network words
Pierre-André Savalle, Rueil-Malmaison (FR); Jean-Philippe Vasseur, Saint Martin d'uriage (FR); and Grégory Mermoud, Venthône (CH)
Assigned to Cisco Technology, Inc., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on May 21, 2021, as Appl. No. 17/327,124.
Application 17/327,124 is a continuation of application No. 16/164,882, filed on Oct. 19, 2018, granted, now 11,025,486.
Prior Publication US 2021/0288876 A1, Sep. 16, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 15/16 (2006.01); H04L 41/16 (2022.01); H04L 41/0806 (2022.01); H04L 67/12 (2022.01); H04L 41/0893 (2022.01); G06F 18/24 (2023.01); G06F 18/214 (2023.01)
CPC H04L 41/16 (2013.01) [G06F 18/214 (2023.01); G06F 18/24 (2023.01); H04L 41/0806 (2013.01); H04L 41/0893 (2013.01); H04L 67/12 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
training, by a device classification service and using feature vectors that represent how frequently one or more traffic features were observed in a network during different time windows among a plurality of time windows, a cascade of machine learning classifiers to label one or more devices in the network with a device type;
receiving, at the device classification service, traffic features of traffic associated with a particular device in the network;
using, by the device classification service, the cascade of machine learning classifiers to assign a device type label to the particular device based on the traffic features of the traffic associated with the particular device; and
initiating, by the device classification service and based on the device type label assigned to the particular device, enforcement of a network policy regarding the particular device.