Asset Classification via User Label Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Enterprises face difficulties in monitoring and detecting potential misuse of assets due to the lack of a clear access level or organizational relationship for assets within identity management systems, making it challenging to track unauthorized access to assets such as laptops or smartphones.
Innovation Solution
A machine-learning-based system that classifies monitored assets using user labels by creating data models that reflect access events, allowing for the detection of potential misuse by identifying assets used by users without the appropriate label, and distinguishing between personal and shared assets using frequency-of-use values and counter-data models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional identity management systems are used to track user access levels, then user access control is maintained, but asset access level tracking is impossible since assets do not have a natural place in identity management systems
Solution Approach 1:
The patent introduces an intermediary component that maps assets to user labels through learned relationships. This intermediary layer enables asset access level tracking without fundamentally restructuring the existing identity management system, resolving the contradiction between maintaining system simplicity and achieving reliable asset tracking.
Solution Approach 2:
The system creates a virtual copy of user label hierarchies and applies them to assets through machine learning. By copying the user label structure and associating it with assets based on access patterns, the system enables asset classification without requiring assets to have native identity management capabilities.
2Measurement precision
If machine learning data models are created to classify assets with user labels, then asset classification accuracy improves, but system complexity and computational resources increase
Solution Approach 1:
The system applies machine learning selectively to specific asset types and user label combinations that benefit most from classification. By implementing partial action rather than comprehensive ML across all assets, the system achieves improved classification accuracy for critical assets while limiting the increase in system complexity and computational overhead.
3Measurement precision
If frequency-of-use thresholds are applied to distinguish personal and shared assets, then asset classification precision improves, but detection time and computational overhead increase
Solution Approach 1:
The system pre-calculates and stores frequency-of-use metrics for assets during normal operation. By performing preliminary action to accumulate usage data before classification decisions are needed, the system enables rapid distinction between personal and shared assets when security events occur, reducing detection time while maintaining classification precision.
Data Source
AI summary
The present disclosure describes a system, method, and computer program for classifying monitored assets based on user labels and for detecting potential misuse of monitored assets based on said classifications. Machine-learning-based modeling is used to classify one or more types of monitored assets with a select user label. A data model is created that reflects monitored assets used by users associated with the select user label. Each a time a user with the select user label accesses an applicable type of monitored asset, the data model is updated to reflect the event. The data model is used to classify one or more monitored assets with the select user label. If a user without the select user label uses a monitored asset classified with the select user label, a potential misuse of the monitored asset is detected.