# US 2026/0087142 A1 · Systems and methods for vulnerability detection and mitigation using artificial intelligence in an electronic environment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0087142 A1 - Document ID: US20260087142A1 - Status: Published application - Kind: A1 - Application number: 18/893,466 - Filed: 2024-09-23 - Published: 2026-03-26 - Earliest claimed: 2024-09-23 - Assignees: Bank of America Corporation - Applicants: Bank of America Corporation - Inventors: Frederick Borcherdt, III - Web page: https://patentgrep.com/patent/US20260087142A1 ## CPC - G06F 21/577: {Assessing vulnerabilities and evaluating computer system security} - H04L 63/1425: {Traffic logging, e.g. anomaly detection} - H04L 63/1433: {Vulnerability analysis} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) ## Abstract Systems, computer program products, and methods are described herein for vulnerability detection and mitigation using artificial intelligence (AI) in an electronic environment. The present disclosure is directed to a system that receives data from at least one data source and generates at least one vulnerability attribute of a network device based on at least the data. In addition, the system applies the vulnerability attribute to an AI engine. Using the AI engine, the system assigns at least one weight to the vulnerability attribute of the network device. After the at least one weight is assigned, the system generates, using the AI engine, a vulnerability matrix of the network device based on the at least one weight. ## Claims ### Claim 1 A system for vulnerability detection and mitigation using artificial intelligence in an electronic environment, the system comprising: a memory device with computer-readable program code stored thereon; at least one processing device, wherein executing the computer-readable program code is configured to cause the at least one processing device to: receive data from at least one data source; generate at least one vulnerability attribute of a network device based on at least the data; apply the vulnerability attribute to an artificial intelligence (AI) engine; assign, by the AI engine, at least one weight to the vulnerability attribute of the network device; and generate, by the AI engine, a vulnerability matrix of the network device based on the at least one weight. ### Claim 2 (depends on 1) The system of claim 1, wherein the data comprises at least one of a compliance data or a regulatory data associated with at least one of network criteria, application criteria, infrastructure criteria, or policy criteria. ### Claim 3 (depends on 1) The system of claim 1, wherein executing the computer-readable program code is further configured to cause the at least one processing device to: generate a forecast engine, wherein the forecast engine comprises a forecast machine learning model; update the forecast engine with the data and the vulnerability matrix; and generate, using the forecast engine, a vulnerability forecasting map. ### Claim 4 (depends on 1) The system of claim 1, wherein executing the computer-readable program code is further configured to cause the at least one processing device to: identify, using a natural language processing (NLP) model, regulatory parameters associated with the data; extract operational data from at least one internal database; generate, using a machine learning (ML) model, a rule threat map based on the regulatory parameters and the operational data; and determine, using the AI engine, remediation recommendations based on the rule threat map. ### Claim 5 (depends on 1) The system of claim 1, wherein executing the computer-readable program code is further configured to cause the at least one processing device to: receive network data packets, wherein the network data packets comprise aggregated vulnerability data; determine, using the AI engine, rule anomalies based on at least the aggregated vulnerability data; create, using the AI engine, a prioritized hierarchy of the rule anomalies based on the vulnerability matrix, wherein the vulnerability matrix comprises vulnerability criteria and a vulnerability threshold; and generate, using the AI engine, a vulnerability matrix remediation based on the prioritized hierarchy of rule anomalies. ### Claim 6 (depends on 5) The system of claim 5, wherein executing the computer-readable program code is further configured to cause the at least one processing device to: receive at least one historical dataset; train the AI engine based on at least one historical dataset, wherein the at least one historical dataset comprises at least one of historical regulatory parameters associated with historical compliance data, historical vulnerability attributes associated with the network device, historical operational objectives associated with historical operational data, historical weights associated with historical vulnerability attributes, or historical vulnerability matrices; receive the aggregated vulnerability data; update the at least one historical dataset with the aggregated vulnerability data; and retrain the AI engine based on the aggregated vulnerability data. ### Claim 7 (depends on 5) The system of claim 5, wherein executing the computer-readable program code is further configured to cause the at least one processing device to: execute the vulnerability matrix remediation; determine, using the AI engine, a confidence threshold associated the vulnerability matrix remediation; compare the confidence threshold to the vulnerability threshold to determine a rule anomaly remediation score; and update the vulnerability matrix with the confidence threshold associated with the vulnerability matrix remediation. ### Claim 8 (depends on 1) The system of claim 1, wherein executing the computer-readable program code is further configured to cause the at least one processing device to: identify, using the AI engine, a rule vulnerability attribute based on the data; identify, using the AI engine, an operational vulnerability attribute; assign, using the AI engine, a rule vulnerability weight for the rule vulnerability attribute and an operational weight for the operational vulnerability attribute; and generate, using the AI engine, a composite vulnerability weight based on the rule vulnerability weight and the operational weight. ### Claim 9 (depends on 1) The system of claim 1, wherein executing the computer-readable program code is further configured to cause the at least one processing device to: generate a user interface on a display, wherein the user interface comprises at least one interactive dashboard; and generate at least one alert based on the vulnerability matrix. ### Claim 10 (depends on 1) The system of claim 1, wherein executing the computer-readable program code is further configured to cause the at least one processing device to: receive control signals from a user device, wherein the control signals comprise a revised mode of the AI engine, a second vulnerability attribute, and a second weight; update the AI engine based on the control signals; and modify the vulnerability matrix. ### Claim 11 A computer program product for vulnerability detection and mitigation using artificial intelligence in an electronic environment, wherein the computer program product comprises at least one non-transitory computer-readable medium having computer-readable program code portion embodied therein, the computer-readable program code portions which when executed by a processing device are configured to cause a processor to: receive data from at least one data source; generate at least one vulnerability attribute of a network device based on at least the data; apply the vulnerability attribute to an artificial intelligence (AI) engine; assign, by the AI engine, at least one weight to the vulnerability attribute of the network device; and generate, by the AI engine, a vulnerability matrix of the network device based on the at least one weight. ### Claim 12 (depends on 11) The computer program product of claim 11, wherein the data comprises regulatory data associated with at least one of network criteria, application criteria, infrastructure criteria, and policy criteria. ### Claim 13 (depends on 11) The computer program product of claim 11, wherein the processing device is further configured to: generate a forecast engine, wherein the forecast engine comprises a forecast machine learning model; update the forecast engine with the data and the vulnerability matrix; and generate, using the forecast engine, a vulnerability forecasting map. ### Claim 14 (depends on 11) The computer program product of claim 11, wherein the processing device is further configured to: identify, using a natural language processing model, regulatory parameters associated with the data; extract operational data from at least one internal database; generate, using a machine learning (ML) model, a rule threat map based on the regulatory parameters and the operational data; and determine, using the AI engine, remediation recommendations based on the rule threat map. ### Claim 15 (depends on 11) The computer program product of claim 11, wherein the processing device is further configured to: receive network data packets, wherein the network data packets comprise aggregated vulnerability data; determine, using the AI engine, rule anomalies based on at least the aggregated vulnerability data; create, using the AI engine, a prioritized hierarchy of the rule anomalies based on the vulnerability matrix, wherein the vulnerability matrix comprises vulnerability criteria and a vulnerability threshold; and generate, using the AI engine, a vulnerability matrix remediation based on the prioritized hierarchy of rule anomalies. ### Claim 16 (depends on 11) The computer program product of claim 11, wherein the processing device is further configured to: identify, using the AI engine, a rule vulnerability attribute based on the data; identify, using the AI engine, an operational vulnerability attribute; assign, using the AI engine, a rule vulnerability weight for the rule vulnerability attribute and an operational weight for the operational vulnerability attribute; and generate, using the AI engine, a composite vulnerability weight based on the rule vulnerability weight and the operational weight. ### Claim 17 (depends on 15) The computer program product of claim 15, wherein the processing device is further configured to: execute the vulnerability matrix remediation; determine, using the AI engine, a confidence threshold associated the vulnerability matrix remediation; compare the confidence threshold to the vulnerability threshold to determine a rule anomaly remediation score; and update the vulnerability matrix with the confidence threshold associated with the vulnerability matrix remediation. ### Claim 18 (depends on 11) The computer program product of claim 11, wherein the processing device is further configured to: receive control signals from a user device, wherein the control signals comprise a revised mode of the AI engine, a second vulnerability attribute, and a second weight; update the AI engine based on the control signals; and modify the vulnerability matrix. ### Claim 19 A computer-implemented method for vulnerability detection and mitigation using artificial intelligence in an electronic environment: receiving data from at least one data source; generating at least one vulnerability attribute of a network device based on at least the data; applying the vulnerability attribute to an artificial intelligence (AI) engine; assigning, by the AI engine, at least one weight to the vulnerability attribute of the network device; and generating, by the AI engine, a vulnerability matrix of the network device based on the at least one weight. ### Claim 20 (depends on 19) The computer-implemented method of claim 19, wherein the computer-implemented method is further configured for: identifying, using a natural language processing model, regulatory parameters associated with the data; extracting operational data from at least one internal database; generating, using a machine learning (ML) model, a rule threat map based on the regulatory parameters and the operational data; and determining, using the AI engine, remediation recommendations based on the rule threat map.