Passive Mobile Authentication via Opportunistic Sensor Sampling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing user authentication methods, such as password-based systems and biometrics, face challenges including user convenience, security, and resource efficiency, particularly in maintaining low resource consumption and avoiding single points of failure.
Innovation Solution
A system that authenticates users based on passive factors by opportunistically collecting and analyzing sensor data from mobile devices, using a model trained with previous user data, and triggering data collection through events like silent push notifications, activity detection, and geofencing, to maintain a low resource footprint.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data is collected frequently for user authentication, then authentication accuracy is improved, but power consumption increases and battery life decreases
Solution Approach 1:
The system implements periodic sensor data collection at predetermined intervals rather than continuous collection. The processor is configured to collect sensor data from sensors at specific time intervals, which reduces power consumption while still maintaining authentication accuracy by regularly updating user identification information.
Solution Approach 2:
The system performs self-service by automatically analyzing collected sensor data to identify users without requiring active user participation. The processor autonomously processes sensor data and compares it against stored profiles to authenticate users, eliminating the need for manual authentication actions while maintaining security.
2Reliability
If sensor data is collected continuously for user identification, then user authentication reliability is improved, but device battery life deteriorates
Solution Approach 1:
The system collects sensor data at predetermined intervals rather than continuously, reducing battery drain while maintaining authentication reliability. This periodic sampling approach ensures that user identification remains accurate without requiring constant sensor operation.
Solution Approach 2:
The system performs preliminary analysis of sensor data to determine whether authentication is necessary before initiating full authentication processes. This allows the system to maintain reliability by pre-processing data and only performing complete authentication when needed, thereby conserving battery life.
3Ease of operation
If passive authentication factors are used, then user convenience is improved, but system complexity increases due to sensor data processing requirements
Solution Approach 1:
The system automatically collects and processes sensor data without requiring active user participation. Users simply need to be present and engaged in normal device usage, while the system autonomously performs authentication, maintaining convenience despite the underlying processing complexity.
Solution Approach 2:
The system merges multiple sensor data streams and authentication functions into a unified processing framework. By combining accelerometer, gyroscope, and other sensor data with user profile information in a single authentication pipeline, the system manages complexity through integration rather than separate processing systems.
Data Source
AI summary
The inventors recently developed a system that authenticates and/or identifies a user of an electronic device based on passive factors, which do not require conscious user actions. During operation of the system, in response to a trigger event, the system collects sensor data from one or more sensors in the electronic device, wherein the sensor data includes movement-related sensor data caused by movement of the portable electronic device while the portable electronic device is in control of the user. Next, the system extracts a feature vector from the sensor data, and analyzes the feature vector to authenticate and/or identify the user. During this process, the feature vector is analyzed using a model trained with sensor data previously obtained from the portable electronic device while the user was in control of the portable electronic device.