Generative AI Security Parameters for Adaptive Vulnerability Assessment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Maintaining up-to-date and relevant security measures for user devices and applications in large networks is challenging due to the dynamic nature of cybersecurity threats and organizational changes, requiring manual intervention and inefficient static questionnaires.

Innovation Solution

A system utilizing generative artificial intelligence (Gen AI) automatically generates and updates data security parameters by integrating historical datasets, user inputs, and real-time threat data to create tailored security questionnaires, adapting to current security and compliance needs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual intervention is used to maintain security parameters, then accuracy and relevance can be ensured, but time consumption and resource consumption increase

Engineering Contradiction:

Improvesecurity parameter accuracyVSAvoidtime consumption

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables self-service by allowing the generative AI engine to automatically generate and update security parameters without requiring manual intervention. The engine processes historical datasets, identifies vulnerabilities, and generates updated parameters autonomously, freeing human resources while maintaining accuracy through AI-driven analysis and continuous learning from historical data.

Inventive Principle:

Principle #25Self-service

2Device complexity

If static questionnaires are used, then simplicity is maintained, but adaptability to evolving security landscapes deteriorates

Engineering Contradiction:

Improvequestionnaire simplicityVSAvoidsecurity parameter adaptability

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The system transforms static questionnaires into dynamic, adaptive structures. The generative AI engine continuously updates security parameters based on real-time vulnerability identification and historical data analysis, allowing the questionnaire to adapt automatically to evolving security landscapes while maintaining a structured format that remains relatively simple to administer.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system implements parameter changes by dynamically modifying security parameter values based on identified vulnerabilities and historical patterns. The generative AI engine adjusts questionnaire parameters such as risk thresholds, compliance requirements, and security controls based on current threat intelligence and organizational context, enabling adaptability without fundamental structural changes.

Inventive Principle:

Principle #35Parameter changes

3Reliability

If manual updates are performed, then control over security parameters is maintained, but productivity decreases

Engineering Contradiction:

Improveparameter controlVSAvoidupdate efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system implements feedback mechanisms where the generative AI engine continuously analyzes historical datasets, identifies security vulnerabilities, and generates updated parameters based on feedback from vulnerability assessments. This automated feedback loop maintains control over security parameters while dramatically improving update efficiency by eliminating manual review and revision cycles.

Inventive Principle:

Principle #23Feedback

4Measurement precision

If comprehensive security assessments are conducted, then assessment accuracy improves, but resource consumption increases

Engineering Contradiction:

Improveassessment accuracyVSAvoidresource consumption

Core Design Contradiction:

Measurement precisionVSQuantity of substance

Solution Approach 1:

The system extracts only the essential information needed for accurate security assessments by using the generative AI engine to identify and focus on critical vulnerabilities and risk factors. The engine processes large historical datasets to extract relevant patterns and generates targeted assessment parameters, improving measurement precision while reducing resource consumption by avoiding unnecessary comprehensive reviews of all security controls.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS20260010641A1Systems and methods for automatically generating and updating data security parameters using generative artificial intelligence

Publication Date: 2026.01.08 BANK OF AMERICA CORP

AI summary

Systems, computer program products, and methods are described herein for automatically generating and updating data security parameters using generative artificial intelligence. The present disclosure is configured to identify a historical dataset comprising at least one historical data security parameter; apply the historical dataset to a generative artificial intelligence (AI) engine; train the generative AI engine based on the application; identify at least user input associated with at least one data security vulnerability; identify at least one current security parameter associated with the at least one data security vulnerability; apply the at least one user input, the at least one data security vulnerability, and the at least one current security parameter to the generative AI engine; generate, by the generative AI engine, an updated security parameter for the current security parameter; and automatically update the current security parameter with the updated security parameter.