Network Device Classification Using Multi-Source Data Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current network device classification methods, particularly in IoT systems, rely on limited metrics like MAC addresses, leading to inaccurate classifications and frequent false positives/negatives, making it difficult to manage access and ensure security across diverse network-connected devices.
Innovation Solution
A system and method for device classification that combines multiple sources of information, including device-specific data, traffic analysis, and external system data, to create detailed and accurate device profiles, enabling precise grouping and application of security policies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sources of information are combined for device classification, then classification accuracy is improved, but device complexity increases
Solution Approach 1:
The classification system is segmented into multiple independent information sources (device-specific data, traffic analysis, external system data) that can be collected and processed separately. Each source contributes specific classification features without requiring the entire system to be reprocessed, allowing accurate classification while managing complexity through modular data collection.
Solution Approach 2:
The classification system is designed to universally accept and process multiple types of information sources simultaneously. The same classification framework handles device-specific data, traffic patterns, and external system information uniformly, enabling accurate multi-factor classification without requiring separate processing systems for each data type.
2Reliability
If multiple sources of information are combined for device classification, then false positives and false negatives are reduced, but information processing requirements increase
Solution Approach 1:
The system extracts only the essential and relevant features from each information source that contribute to classification accuracy. Rather than processing all available data, the system identifies and extracts key classification indicators from device-specific data, traffic analysis, and external systems, reducing data volume while maintaining reliability.
Solution Approach 2:
The system implements partial processing by focusing on the most critical information sources and classification features needed for accurate device categorization. Rather than exhaustively analyzing all possible data points, the system processes sufficient information to achieve reliable classification without unnecessary data handling overhead.
Data Source
AI summary
Systems, methods, and related technologies for device classification are described. Methods include determining device information associated with a device coupled to a network, the device information including information obtained from one or more sources, classifying the device using the device information as input to a classifier, and applying a policy to the device based on the classification of the device.