US 11,985,136 B2
System for detection and classification of intrusion using machine learning techniques
Scott Anderson Sims, Tega Cay, SC (US); Jeffrey Brian Bashore, Saint Augustine, FL (US); Jeffrey David Finocchiaro, Newark, DE (US); and Craig Douglas Widmann, Chandler, AZ (US)
Assigned to BANK OF AMERICA CORPORATION, Charlotte, NC (US)
Filed by BANK OF AMERICA CORPORATION, Charlotte, NC (US)
Filed on Nov. 30, 2022, as Appl. No. 18/072,526.
Application 18/072,526 is a continuation of application No. 17/181,608, filed on Feb. 22, 2021, granted, now 11,563,744.
Prior Publication US 2023/0089968 A1, Mar. 23, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 9/40 (2022.01); G06F 18/24 (2023.01); G06N 20/00 (2019.01)
CPC H04L 63/102 (2013.01) [G06F 18/24 (2023.01); G06N 20/00 (2019.01); H04L 63/1441 (2013.01); H04L 63/20 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A system for detection and classification of intrusion using machine learning techniques, the system comprising:
at least one non-transitory storage device comprising program instructions stored thereon; and
at least one processing device coupled to the at least one non-transitory storage device, wherein the program instructions are configured to cause the at least one processing device to perform the following operations:
electronically receive, from a computing device of a user, an indication that the user has initiated a first resource interaction;
retrieve information associated with the first resource interaction, wherein the information comprises at least one or more parameters associated with the first resource interaction;
initiate a machine learning model on the one or more parameters associated with the first resource interaction, wherein the machine learning module is trained by: retrieving one or more parameters associated with one or more historical resource interactions and one or more class labels associated with one or more classes; initiating one or more machine learning algorithms on the one or more parameters associated with the one or more historical resource interactions and the one or more class labels; and training, using the one or more machine learning algorithms, the machine learning model, wherein training comprises determining one or more classification parameters for the machine learning model; and
classify, using the machine learning model, the first resource interaction into the one or more classes, wherein the one or more classes comprises one or more access types.