Data Driven Device Detection Using Probability Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing device detection techniques in network communication systems face challenges due to changing device features over time, making accurate identification difficult, especially in security and authentication contexts where reliability and reduced false positives are crucial.
Innovation Solution
The implementation of data-driven device detection techniques that involve obtaining feature values, calculating probability values for potential devices, identifying a candidate device with a maximum probability, and labeling it based on a predefined threshold, which can vary depending on user history and device similarity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If device detection is performed using device features such as installed applications, hardware characteristics and configuration values, then device identification can be achieved, but the detection accuracy deteriorates over time as these features change
Solution Approach 1:
The system performs preliminary actions by continuously monitoring and recording device features over time before detection is needed. Historical feature data is collected and stored, creating a baseline profile that can be compared against future states to detect changes and maintain accurate device identification despite feature evolution
Solution Approach 2:
The system implements feedback mechanisms where device detection results and feature changes are continuously monitored. When feature changes are detected, the system adjusts its detection model by incorporating new historical data, creating a closed-loop system that adapts to maintaining accuracy over time
2Reliability
If strict device detection thresholds are applied to ensure security, then false positive rate increases, but if lower thresholds are applied, then detection reliability decreases
Solution Approach 1:
The system applies partial action by using different detection thresholds for different devices based on their historical behavior patterns. Instead of a uniform strict threshold, the system adjusts the detection sensitivity partially according to each device's profile, allowing more lenient thresholds for reliable devices and stricter thresholds for suspicious ones, thereby reducing false positives while maintaining overall detection reliability
Solution Approach 2:
The system dynamically changes detection parameters including thresholds based on historical data analysis. The threshold is not fixed but adapts according to the device's behavioral patterns, risk profile, and historical reliability, allowing the system to optimize the balance between detection reliability and false positive reduction for each specific case
Data Source
AI summary
Data driven device detection is provided, whereby a device is detected by obtaining a plurality of feature values for a given device; obtaining a set of device attributes for a plurality of potential devices; calculating a probability value that the given device is each potential device within the plurality of potential devices; identifying a candidate device associated with a maximum probability value among the calculated probability values; and labeling the given device as the candidate device if the associated maximum probability value satisfies a predefined threshold. The predefined threshold can be a function, for example, of whether the given user has previously used this device. The obtained feature values can be obtained for a selected set of features satisfying one or more predefined characteristic criteria. The device attributes can be obtained, for example, from a profile for each of the plurality of potential devices.