US 12,073,209 B2
System for enhanced component-level detection in software applications within a computing environment
Tomas M. Castrejon, III, Fort Mill, SC (US); Manu Jacob Kurian, Dallas, TX (US); David Nardoni, Sierra Madre, CA (US); Joel Townsend, Spring Church, PA (US); and Michael Robert Young, Davidson, NC (US)
Assigned to BANK OF AMERICA CORPORATION, Charlotte, NC (US)
Filed by BANK OF AMERICA CORPORATION, Charlotte, NC (US)
Filed on Mar. 29, 2022, as Appl. No. 17/706,781.
Prior Publication US 2023/0315439 A1, Oct. 5, 2023
Int. Cl. G06F 8/70 (2018.01); G06F 21/57 (2013.01); G06N 5/022 (2023.01)
CPC G06F 8/70 (2013.01) [G06F 21/577 (2013.01); G06N 5/022 (2013.01); G06F 2221/033 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A system for enhanced component-level detection in software applications, the system comprising:
at least one non-transitory storage device; and
at least one processor coupled to the at least one non-transitory storage device, wherein the at least one processor is configured to:
receive, from a client device, one or more data packets with payload containing a request to onboard a first application into a computing environment;
determine, using an application ingestion subsystem, information associated with the first application;
train, using a machine learning subsystem, a machine learning model using known information associated with one or more applications, one or more known components associated with the one or more applications, and one or more known component scanning parameters;
deploy, using the machine learning subsystem, the trained machine learning model on the information associated with the first application;
determine, using the trained machine learning model, one or more components associated with the first application and one or more component scanning parameters for each of the one or more components;
determine one or more elements associated with each of the one or more components;
build a software bill of materials (SBOM) for the first application based on at least the one or more elements associated with each of the one or more components;
determine, using a vulnerability scanning engine, one or more software vulnerabilities associated with the one or more elements associated with each of the one or more components of the first application, wherein the one or more software vulnerability issues comprises at least changes in systems and critical system files in each element indicating an application compromise;
retrieve, from a first repository, one or more mitigation actions for the one or more software vulnerabilities; and
automatically execute, using the application ingestion subsystem, the one or more mitigation actions.