Robert E Klein

US Patent:

20200401941, Dec 24, 2020

Filed:

Jun 29, 2020

Appl. No.:

16/916049

Inventors:

- Philadelphia PA, US
Robert H. Klein - Silver Spring MD, US
Ryan V. Peters - Fairfax VA, US
Peter E. Kaloroumakis - Bowie MD, US

International Classification:

G06N 20/00
G06N 5/04
G06F 21/56
H04W 12/12

Abstract:

A system and method for batched, supervised, in-situ machine learning classifier retraining for malware identification and model heterogeneity. The method produces a parent classifier model in one location and providing it to one or more in-situ retraining system or systems in a different location or locations, adjudicates the class determination of the parent classifier over the plurality of the samples evaluated by the in-situ retraining system or systems, determines a minimum number of adjudicated samples required to initiate the in-situ retraining process, creates a new training and test set using samples from one or more in-situ systems, blends a feature vector representation of the in-situ training and test sets with a feature vector representation of the parent training and test sets, conducts machine learning over the blended training set, evaluates the new and parent models using the blended test set and additional unlabeled samples, and elects whether to replace the parent classifier with the retrained version.

US Patent:

20190311285, Oct 10, 2019

Filed:

Nov 5, 2018

Appl. No.:

16/180790

Inventors:

- Philadelphia PA, US
Robert H. Klein - Silver Spring MD, US
Ryan V. Peters - Fairfax VA, US
Peter E. Kaloroumakis - Bowie MD, US

International Classification:

G06N 20/00
G06N 5/04
G06F 21/56
H04W 12/12

Abstract:

A system and method for batched, supervised, in-situ machine learning classifier retraining for malware identification and model heterogeneity. The method produces a parent classifier model in one location and providing it to one or more in-situ retraining system or systems in a different location or locations, adjudicates the class determination of the parent classifier over the plurality of the samples evaluated by the in-situ retraining system or systems, determines a minimum number of adjudicated samples required to initiate the in-situ retraining process, creates a new training and test set using samples from one or more in-situ systems, blends a feature vector representation of the in-situ training and test sets with a feature vector representation of the parent training and test sets, conducts machine learning over the blended training set, evaluates the new and parent models using the blended test set and additional unlabeled samples, and elects whether to replace the parent classifier with the retrained version.

US Patent:

20170032279, Feb 2, 2017

Filed:

Jun 8, 2016

Appl. No.:

15/176784

Inventors:

- McLean VA, US
Robert H. Klein - Silver Spring MD, US
Ryan V. Peters - Elkridge MD, US
Peter E. Kaloroumakis - Columbia MD, US

International Classification:

G06N 99/00
G06F 21/56
G06N 5/04

Abstract:

A system and method for batched, supervised, in-situ machine learning classifier retraining for malware identification and model heterogeneity. The method produces a parent classifier model in one location and providing it to one or more in-situ retraining system or systems in a different location or locations, adjudicates the class determination of the parent classifier over the plurality of the samples evaluated by the in-situ retraining system or systems, determines a minimum number of adjudicated samples required to initiate the in-situ retraining process, creates a new training and test set using samples from one or more in-situ systems, blends a feature vector representation of the in-situ training and test sets with a feature vector representation of the parent training and test sets, conducts machine learning over the blended training set, evaluates the new and parent models using the blended test set and additional unlabeled samples, and elects whether to replace the parent classifier with the retrained version.