Network Device Type Prediction for Dynamic Security Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network mapping technologies struggle to accurately and dynamically determine the type of devices within a network due to changes in device configurations over time, leading to inefficiencies in network security and management.
Innovation Solution
Utilizing a trained machine learning module to assign unique identification codes, calculate confidence scores, and determine type information for devices within a network, incorporating a semi-supervised model framework to predict and dynamically update device types based on digital fingerprints and historical data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional network mapping methods are used to identify devices, then the process is simple and direct, but the accuracy of device type determination deteriorates due to device configuration changes over time
Solution Approach 1:
The patent implements dynamic device type determination by continuously monitoring device behaviors and configurations over time. The system updates device type classifications dynamically based on observed changes in device behaviors, network traffic patterns, and configuration parameters, allowing the system to adapt to device evolution without manual reclassification.
Solution Approach 2:
The patent employs historical data collection and baseline establishment before formal device type determination. The system accumulates device behavior data over predetermined periods, establishes usage baselines, and performs preliminary analysis to improve the accuracy of subsequent device type classifications and change detection.
2Productivity
If device type labeling is performed manually, then the system complexity is low, but the productivity and real-time response capability deteriorate
Solution Approach 1:
The patent implements automated self-service device type determination where the system autonomously collects device data, analyzes behaviors, determines device types, and updates classifications without human intervention. The system automatically detects configuration changes and reclassifies devices based on observed behaviors, eliminating manual labeling requirements.
Solution Approach 2:
The patent incorporates continuous feedback loops where device behavior data is collected, analyzed against established baselines, and used to update device type classifications. The system monitors the effectiveness of classifications and adjusts them based on observed deviations from expected behaviors, enabling continuous improvement of determination accuracy.
3Measurement precision
If comprehensive device scanning is performed to ensure accurate type identification, then the measurement precision improves, but the loss of time increases due to extensive scanning requirements
Solution Approach 1:
The patent performs preliminary data collection during normal network operations over predetermined periods before formal device type determination is required. By accumulating device behavior data in advance during routine network activity, the system reduces the need for extensive scanning at the time of classification, thereby improving accuracy without significant time loss.
Solution Approach 2:
The patent implements continuous device monitoring and data collection as part of normal network operations. Instead of performing discrete, time-consuming scans, the system continuously gathers device behavior data, network traffic information, and configuration parameters during regular network activity, enabling accurate device type determination without interrupting network operations or requiring dedicated scanning time.
Data Source
AI summary
In some embodiments, the present disclosure provides an exemplary method that may include steps of obtaining data associated with a device within a network; determining a software being performed via type information of the device based on a scan of the network and data associated with the device; generating a type label for the device based on the software being performed; and generating, by the processor, a network security map that represents a topology of the network, wherein the network security map maps the device within the topology according to the type label so as to facilitate causing at least one security action with respect to the device within the network.