US 12,088,610 B2
Platform for privacy preserving decentralized learning and network event monitoring
Madhusoodhana Chari Sesha, Bangalore (IN); Krishna Prasad Lingadahalli Shastry, Bangalore (IN); and Sathyanarayanan Manamohan, Bangalore (IN)
Assigned to Hewlett Packard Enterprise Development LP, Spring, TX (US)
Filed by HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP, Houston, TX (US)
Filed on Oct. 27, 2021, as Appl. No. 17/512,609.
Prior Publication US 2023/0130705 A1, Apr. 27, 2023
Int. Cl. H04L 9/40 (2022.01)
CPC H04L 63/1425 (2013.01) [H04L 63/145 (2013.01); H04L 63/1466 (2013.01); H04L 63/1483 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, at a network device, a set of flow behaviors for data flow traffic;
applying, at the network device, a machine learning (ML) model that comprises labelled network tuples and signatures for flow behaviors to the set of flow behaviors, wherein output from the machine learning model predicts a classified label for a particular data flow of the data flow traffic;
determining, at the network device, an implicit label for a network tuple parameter for the particular data flow, wherein the implicit label comprises a reported value in a packet header of the particular data flow;
comparing the classified label for the network tuple parameter to the implicit label; and
perform an action associated with the comparison.