ML Model for Automatic Critical Network Asset Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to automatically and effectively identify critical network assets in private computer networks, which are essential for enhanced security and network functionality.
Innovation Solution
A machine learning model is trained using histograms of features aggregated from log entries to predict whether a network asset is critical, with the model being deployed and retrained within the network to improve prediction accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual identification methods are used to determine critical network assets, then security personnel can assess asset importance, but the process is time-consuming and prone to human error
Solution Approach 1:
The patent replaces manual mechanical assessment processes with an automated machine learning system. The ML model processes log data and automatically identifies critical assets, eliminating human intervention in the assessment process. This substitution achieves both higher accuracy through consistent algorithmic evaluation and reduced time through automated processing of large datasets.
Solution Approach 2:
The system enables the network infrastructure to self-identify its own critical assets through automated analysis of operational data. The ML model continuously monitors log entries and autonomously determines asset criticality without requiring external manual assessment, allowing the system to serve its own security identification needs.
2Measurement precision
If comprehensive log data is collected from all network assets, then more accurate predictions can be made, but data processing complexity and computational resources increase
Solution Approach 1:
The patent extracts only the most relevant features from comprehensive log data using the ML model. Instead of processing all raw log entries equally, the system identifies and extracts key predictive features that indicate asset criticality. This extraction maintains high prediction accuracy while reducing the complexity of data processing by focusing on essential information.
Solution Approach 2:
The system transforms raw log data into meaningful features through parameter changes in the ML processing pipeline. By converting raw data into standardized feature representations and applying various transformations, the system maintains comprehensive data utilization while managing computational complexity through structured parameter management.
Data Source
AI summary
Critical network assets of a private computer are automatically identified by training a machine learning model with histograms of features obtained by aggregating data of log entries. The model is deployed in a private computer network and retrained using training data set of the private computer network. Data from log entries of a target network asset are aggregated, numerically transformed, and converted into features histograms. The features histograms are concatenated into a single file, which is provided to the machine learning model for prediction. The machine learning model outputs a prediction score that gives an indication of whether or not the target network asset is critical.