Biometric Verification via Eye Tracking and Audio
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional user verification methods rely on single forms of protection, making them vulnerable to adversaries and often delay the verification process, while not ensuring the liveliness of the user, allowing for potential impersonation using prefabricated credentials.
Innovation Solution
A method that gathers multiple verification credentials simultaneously, including captured images, audio, and tracked eye movement, to ensure the liveliness of the user and prevent impersonation, using a verification platform that communicates between primary and secondary devices to enhance security and reduce verification time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple forms of identification are required for verification, then security is improved, but the verification process time increases significantly
Solution Approach 1:
The patent combines multiple verification credentials (facial recognition, voice recognition, eye movement tracking) into a single integrated verification process. These credentials are gathered simultaneously rather than sequentially, merging what would traditionally be separate verification steps into one concurrent operation, thereby maintaining high security while reducing total verification time.
Solution Approach 2:
The system performs preliminary actions by continuously monitoring and pre-processing verification credentials in the background before they are formally required. Eye movement tracking and other biometric data are gathered in advance, so when verification is needed, the credentials are already available for immediate analysis, reducing the perceived verification time.
2Ease of operation
If traditional verification methods are used, then the verification process is simple, but they do not ensure the liveliness of the user, allowing impersonation
Solution Approach 1:
The patent introduces randomized visual patterns as an intermediary element between the user and the verification system. These dynamic patterns serve as a mediator that requires active user engagement (tracking moving patterns with eyes), providing liveness verification while maintaining ease of operation. The patterns act as a bridge that simultaneously achieves simplicity and reliability.
Solution Approach 2:
The verification system employs dynamic, moving visual patterns rather than static images. These patterns move randomly across the screen and require continuous eye tracking, creating a dynamic verification process that is both simple for the user to perform and effective at detecting liveness. The motion and randomness prevent automation while maintaining user-friendly operation.
3Reliability
If randomized verification patterns are used to ensure liveliness, then security against impersonation is improved, but device complexity increases
Solution Approach 1:
The patent implements a universal verification system where a single set of eye tracking and visual pattern display capabilities serves multiple verification functions. The same hardware components (camera, display, processor) used for basic facial recognition are also used for liveness detection through eye movement tracking, eliminating the need for separate dedicated hardware and reducing overall system complexity despite enhanced security capabilities.
Data Source
AI summary
In one embodiment, a method comprises receiving a verification request, sending one or more patterns for display at one or more specified locations on a screen of a device, receiving verification input responsive to the one or more patterns, and granting or denying the verification request based at least in part on the verification input. The verification input comprises one or more captured images, captured audio and tracked eye movement. The verification request may be generated in conjunction with an attempted launch of a designated application on a first device, with user access to the designated application on the first device being controlled responsive to the granting or denying of the verification request.