US 12,250,239 B2
Online anomaly detection of vector embeddings
Giacomo Bernardi, Varese (IT); Donagh Horgan, Cork (IE); Jeffrey W. Haskell, New Boston, NH (US); and Markus Nispel, Boston, MA (US)
Assigned to Extreme Networks, Inc., San Jose, CA (US)
Filed by Extreme Networks, Inc., San Jose, CA (US)
Filed on Oct. 18, 2023, as Appl. No. 18/489,097.
Application 18/489,097 is a continuation of application No. 16/778,585, filed on Jan. 31, 2020, granted, now 11,824,876.
Prior Publication US 2024/0064165 A1, Feb. 22, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 9/40 (2022.01); G06F 21/55 (2013.01)
CPC H04L 63/1425 (2013.01) 20 Claims
OG exemplary drawing
 
1. A method, comprising:
determining, by at least one processor of an anomaly detection system, a maximum similarity value as a maximum of a plurality of similarity values between a flow vector and a plurality of flow clusters associated with a network device;
comparing, by the at least one processor of the anomaly detection system, the maximum similarity value to a threshold, wherein the threshold is based on a minimum confidence threshold; and
in response to the maximum similarity value being less than the threshold:
detecting an anomaly in the network device;
generating an alert message based on the detected anomaly; and
generating a new flow cluster based on the flow vector, wherein the new flow cluster is stored in a memory for a subsequent anomaly detection.