Mobile Device Authentication Using Sensor Fusion for Liveness Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current user authentication methods for mobile devices are inadequate in distinguishing between genuine users and attackers, particularly in scenarios where power consumption and security risks are high, and they often rely on insecure third-party applications that can be compromised.
Innovation Solution
A system that utilizes a combination of touch data and acceleration/gyroscope data to generate user-specific traits, correlating these traits to authenticate users and differentiate between legitimate and fraudulent users, while also incorporating liveness and freshness detection for image or video authentication, and selectively activating the camera to conserve power.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional authentication methods (username/password) are used, then ease of operation is maintained, but security reliability deteriorates due to susceptibility to attacks and compromises
Solution Approach 1:
The system automatically captures touch data and acceleration data from the device sensors during normal user interaction, eliminating the need for separate authentication actions. The authentication process happens passively through analysis of natural device usage patterns, making it both secure and convenient
Solution Approach 2:
The patent replaces traditional mechanical authentication methods (typing passwords, entering PINs) with sensor-based detection systems that analyze touch patterns and device acceleration. This substitution enables more reliable authentication through objective biometric data rather than subjective user input
2Reliability
If camera is continuously activated for image authentication, then authentication reliability improves through liveness detection, but power consumption increases
Solution Approach 1:
The camera is activated periodically only when needed for image capture during authentication, rather than continuously. The system uses acceleration data to detect when the device is being held in an authentication posture, triggering camera activation only at these specific moments, thus reducing overall power consumption while maintaining authentication reliability
Solution Approach 2:
The acceleration sensor acts as an intermediary that monitors device state and triggers camera activation only when authentication conditions are met. This intermediary mechanism ensures the camera operates only when necessary, balancing liveness detection accuracy with power conservation
3Reliability
If multiple authentication factors are required, then security reliability improves, but device complexity and operation time increase
Solution Approach 1:
The patent combines multiple authentication factors (touch data from touchscreen, acceleration data from motion sensors, and optionally image data from camera) into a unified authentication system. These diverse data sources are integrated and analyzed together to generate a comprehensive authentication decision, improving security while managing complexity through unified processing
4Ease of operation
If third-party authentication applications are used, then ease of operation is maintained, but security reliability deteriorates due to potential compromises
Solution Approach 1:
The authentication functionality is implemented as a built-in system service within the device itself, using native sensors and processing capabilities. This eliminates dependency on external third-party applications, ensuring that authentication security is managed directly by the device manufacturer and cannot be compromised by external apps
Data Source
AI summary
System, method, and device of detecting identity of a user and authenticating a user; as well as detecting a possible attacker or impostor, and differentiating among users of an electronic device or of a computerized service. A mobile or portable electronic device is utilized to capture a self-taken image of a user, which is utilized as a user-authentication factor. The accelerometer and gyroscope of the mobile device, sense and measure spatial device properties during, before or after the submission of the self-image authentication factor; and based on such spatial device properties, the system determines liveness of the user, freshness of the submitted self-image, and possibly differentiates between a legitimate user and an attacker. Similarly, spatial device properties that accompany the entry or the submission of a biometric sample, such as fingerprint scan or retina scan, are used to detect liveness or freshness or authenticity of such biometric samples, and are used to differentiate between a legitimate user and an attacker.