Adaptive Biometric Matching Model for Authentication Security

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Biometric authentication systems face degradation in recognition performance and vulnerability to spoofing attacks when user reference biometric information is updated based on received biometric data, especially in portable electronic devices providing financial services.

Innovation Solution

An electronic device equipped with a biometric sensor and processor that identifies the security level of a service and determines a confidence level of user biometric data to select an appropriate matching model for authentication, allowing for dynamic adaptation of biometric data templates and reducing misrecognition rates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If user reference biometric information is updated based on received biometric data, then authentication adaptability is improved, but recognition performance degrades and spoofing vulnerability increases

Engineering Contradiction:
Improveauthentication adaptabilityVSAvoidrecognition performance
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent applies local quality by differentiating between high-security services and other services in determining whether to update reference biometric information. For high-security services, the system maintains original reference data without updates, while allowing updates for other services. This localized application of update logic resolves the contradiction by preserving recognition performance for critical services while maintaining adaptability for less critical ones.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system performs preliminary assessment of service security levels before deciding whether to update reference biometric information. By evaluating the security level in advance and pre-determining the appropriate matching model, the system prevents premature or inappropriate updates that would degrade recognition performance, while still enabling updates when safe to do so.

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If biometric data templates are dynamically adapted, then authentication flexibility is improved, but system complexity increases

Engineering Contradiction:
Improveauthentication flexibilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent changes the parameter of reference biometric information update based on service security levels. By using different update strategies (update vs. no update) depending on the service type, the system achieves flexible authentication without implementing a completely complex dynamic update mechanism for all cases. This selective parameter change simplifies the overall system complexity.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system implements dynamics by making the reference biometric information update process conditional and adaptive to service requirements. Rather than a static all-or-nothing update approach, the system dynamically adjusts its behavior based on service security levels, achieving flexibility only where needed while maintaining simplicity for standard cases.

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If matching model is selected based on security level and confidence level, then authentication accuracy is improved, but processing time increases

Engineering Contradiction:
Improveauthentication accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies partial action by selecting matching models based on service security levels rather than always using the most accurate model. For high-security services, the system uses more accurate matching models, while using simpler models for low-security services. This partial application of high-accuracy processing only where necessary reduces overall processing time while maintaining accuracy when critical.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system performs preliminary determination of service security levels and pre-selects appropriate matching models before actual authentication processing. By preparing the matching model selection in advance based on service type, the system avoids time-consuming model selection during the actual authentication process, reducing processing time while maintaining accuracy.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3884407B1Electronic device for authenticating biometric information and operating method thereof
Publication Date: 2023.10.25 SAMSUNG ELECTRONICS CO LTD
  • EP3884407B1 patent drawingFigure 1
  • EP3884407B1 patent drawingFigure 2~3
  • EP3884407B1 patent drawingFigure 4

AI summary

Various embodiments of the disclosure relate to an electronic device for determining a matching model used to authenticate biometric information, and an operating method thereof. An electronic device according to various embodiments of the disclosure may include a biometric sensor, and a processor operatively coupled with the biometric sensor. The processor may be configured to identify a security level of a service requested to be executed, determine a confidence level of user's biometric data received via the biometric sensor, determine a matching model to be used to authenticate the received user's biometric data based on the identified security level and the determined confidence level, and authenticate the received user's biometric data based on the determined matching model. Various other embodiments are also possible.