Cloud Resource Criticality Scoring Using ML Resource Classes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Cloud resources managed by organizations often span multiple internal organizations and teams, making it difficult to determine which resources are critical for business operations, and existing vulnerability management systems assign criticality scores based on simple rule-based methodologies that lack precision.
Innovation Solution
A method using machine-learning (ML)-based classifiers and regressors, trained with rule-based heuristics, to derive resource criticality scores for cloud resources by converting information samples into vectorized data, determining probability distributions, and normalizing scores based on cloud resource classes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If rule-based methodology is used to assign criticality scores to cloud resources, then the process is simple and fast, but the precision and accuracy of the scores are insufficient
Solution Approach 1:
The patent transforms the criticality scoring process from rule-based to machine-learning-based, changing the fundamental parameter of how scores are generated. The ML models analyze multiple attributes (cost, security controls, configuration) to produce more precise criticality scores that reflect actual business impact, resolving the contradiction between precision and complexity by using data-driven approaches instead of simple rules
Solution Approach 2:
The patent introduces an intermediary layer of machine learning models that act as mediators between raw cloud resource data and criticality scores. These ML-based classifiers and regressors process information samples, convert them to vectorized data, and generate explainable scores, thereby improving precision while managing complexity through a structured intermediate processing layer
2Ease of operation
If cloud resources are managed directly by a single system administrator, then control is centralized, but management becomes difficult as resources span multiple internal organizations and teams
Solution Approach 1:
The patent changes the management approach from centralized administrator control to automated ML-driven criticality assessment. By transforming how resources are evaluated (using cost information, security controls, configuration data), the system makes management easier despite the complexity of multi-organizational cloud infrastructures
Solution Approach 2:
The patent enables cloud resources to effectively self-assess their criticality through ML models that automatically analyze their own attributes and generate scores. This self-service approach eliminates the need for a single administrator to manually evaluate each resource, making management easier while handling complex multi-organizational environments
3Adaptability or versatility
If cloud infrastructure is expanded to support more resources, then business flexibility increases, but the attack surface and security vulnerability detection difficulty increase
Solution Approach 1:
The patent changes the detection methodology from manual or rule-based to ML-based analysis of multiple parameters (cost, security controls, configuration). This allows the system to handle expanded cloud infrastructure and increased attack surfaces by automatically analyzing diverse resource attributes to identify critical vulnerabilities
Solution Approach 2:
The patent implements feedback mechanisms where ML models continuously analyze cloud resource attributes and generate criticality scores that inform security priorities. This feedback loop enables the system to adapt to expanding infrastructure by automatically detecting and prioritizing vulnerabilities based on business criticality
Data Source
AI summary
In an aspect, a machine-learning (ML)-based classifier or regressor associated with a respective cloud resource class by is trained inputting information samples and resource criticality scores for the respective cloud resource class as training data. In a further aspect, the ML-based classifier or regressor is further utilized to assign a resource criticality score to a particular cloud resource in the respective cloud resource class.