Probabilistic Mobile Device Authentication via Sensor Coherence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional mobile device authentication methods, such as locking and requiring login credentials or fingerprints, can be inconvenient, especially when the device has remained in the user's possession for an extended period, as they necessitate reauthentication even when the device is still with the owner.
Innovation Solution
A system and method that analyzes sensor data from various devices to determine the probability of user possession, using a probabilistic model to decide whether to require authentication, allowing for passive or active authentication based on the coherence of sensor data from multiple devices, including motion, location, and bio sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the mobile device is locked and requires login credentials or fingerprint each time, then the security level is improved, but the ease of operation deteriorates
Solution Approach 1:
The system automatically determines user possession probability by analyzing sensor data from multiple devices without requiring manual authentication input. The device self-assesses whether authentication is needed based on contextual information from motion sensors, location sensors, and other sensors, eliminating the need for users to manually provide credentials or fingerprints.
Solution Approach 2:
The system continuously monitors sensor data from multiple devices and uses this feedback to dynamically update the probability of user possession. Based on this feedback loop, the system automatically adjusts authentication requirements, allowing convenient access when possession is confirmed and maintaining security when possession is uncertain.
2Reliability
If the device requires reauthentication even when still with the user, then the security level is improved, but the loss of time increases
Solution Approach 1:
The system performs preliminary analysis of sensor data from multiple devices to determine the probability of user possession before authentication is actually required. By proactively assessing possession probability based on contextual information, the system can preemptively clear authentication requirements when the user is confirmed to be present, avoiding unnecessary authentication delays.
Solution Approach 2:
The system changes the parameter of authentication requirement based on the calculated probability of user possession. When the probability exceeds a threshold, the system changes the authentication state from required to not required, allowing seamless access without time-consuming reauthentication even when the device remains with the user.
3Measurement precision
If the device uses multiple sensors to determine possession probability, then the measurement precision is improved, but the device complexity increases
Solution Approach 1:
The system uses a multi-functional approach where a single probabilistic model integrates data from multiple sensor types (motion sensors, location sensors, bio sensors) to serve multiple purposes: determining user presence, assessing possession probability, and triggering appropriate authentication responses. This universal model handles diverse sensor inputs through a unified processing framework.
Solution Approach 2:
The system merges data from multiple sensor sources and multiple devices into a single integrated possession probability assessment. By combining motion data, location data, and bio sensor data from various devices, the system creates a comprehensive view of user possession that is more accurate than any single sensor could provide alone.
Data Source
AI summary
Method and systems for modeling user possession of a mobile device for a user authentication framework are provided. The method includes analyzing sensor data representing information captured from sensor(s) associated with at least one of a plurality of devices, the plurality including the user's mobile device. The method allows for determining, based on the analyzed sensor data, a probability that the user maintains possession of the user's mobile device; and configuring the probability for use in determining whether to require authentication. The determination may include configuring a probabilistic model that includes a first state indicating that the user possesses the mobile device and a second state indicating that the user does not; classifying motions of the mobile device by types, the motions being determined based on the sensor data; and updating probabilities of the two states in response to determining that at least one of the motions has occurred.