IoT Device Identification via Passive Network Traffic Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing device identification methods for IoT devices are unreliable as they interrupt services by requiring the device to report information, leading to low service reliability.
Innovation Solution
Determine the network traffic feature of IoT devices based on data packet amounts collected within periodicities using a device identification model, without requiring the device to report identifying information, thus maintaining service reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If device identification is performed by requiring the device to report information, then device type recognition can be achieved, but service reliability deteriorates due to service interruption
Solution Approach 1:
The patent introduces a management device as an intermediary that performs device identification by analyzing network traffic data collected from the network, rather than requiring direct interaction with the to-be-identified device. The management device collects data packets, extracts features, and determines device types without the target device needing to report information or interrupt its services.
Solution Approach 2:
The patent replaces the mechanical interaction method (where the device must actively report information) with a passive observation method using network traffic analysis. By substituting the active reporting mechanism with passive packet capture and feature extraction from network traffic, the system achieves device identification without interrupting device operations.
2Reliability
If network traffic data is collected and analyzed, then service reliability is maintained, but identification complexity increases due to data processing requirements
Solution Approach 1:
The patent extracts only the essential features from network traffic data that are necessary for device identification, such as packet length distribution, inter-packet time intervals, and protocol types. By taking out and focusing on these key features rather than processing all raw traffic data, the system maintains reliability while reducing processing complexity.
Solution Approach 2:
The patent segments the device identification process into distinct modules: data collection, feature extraction, and device type determination. This segmentation allows each module to be optimized independently, managing overall system complexity while maintaining service reliability through systematic data processing.
Data Source
AI summary
A device identification method, apparatus, and system are provided. A management device or a collection device first determines a network traffic feature of a to-be-identified device based on a first dataset. The first dataset includes a plurality of pieces of first data, and each piece of first data includes a data amount of a data packet that is of the to-be-identified device and that is collected within one first periodicity. Then, the management device or the collection device determines a device type of the to-be-identified device based on a device identification model and the network traffic feature of the to-be-identified device.