Distance-Preserving Biometric Data Transformation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Biometric authentication systems face challenges such as user registration complexity across multiple devices, storage security concerns, and reduced accuracy due to minor differences in biometric data, which existing methods like encryption and hash functions fail to adequately address.

Innovation Solution

Implementing distance-preserving transformations that map biometric data into a new metric space while maintaining original distances, allowing for secure comparison without decryption or multiple exemplars, thus enhancing authentication efficiency and security.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If encryption or hash functions are used to secure biometric templates, then storage security is improved, but authentication accuracy deteriorates due to inability to perform direct comparison

Engineering Contradiction:
Improvestorage securityVSAvoidauthentication accuracy
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent transforms biometric templates using distance-preserving functions that change the parameter space while maintaining the metric relationships between templates. This allows secure storage of transformed templates that can still be directly compared during authentication, resolving the contradiction between security and accuracy.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If multiple exemplar biometric templates are stored to account for variations, then authentication reliability is improved, but device complexity and storage requirements increase

Engineering Contradiction:
Improveauthentication reliabilityVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces distance-preserving transformation functions as intermediaries that map biometric templates into a new metric space. This single transformed template serves as a universal reference that accommodates natural biometric variations without requiring multiple exemplars, thus reducing system complexity while maintaining reliability.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If biometric data is transformed into encrypted form, then security is improved, but authentication time increases due to decryption requirements

Engineering Contradiction:
ImprovesecurityVSAvoidauthentication time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent applies distance-preserving transformations during the initial template creation and storage phase, preparing the data in advance in a secure yet directly comparable format. This eliminates the need for time-consuming decryption operations during authentication, as the transformed templates can be compared directly in their transformed state.

Inventive Principle:
Principle #10Preliminary action

4Ease of operation

If traditional password-based authentication is used, then ease of operation is improved, but security deteriorates due to vulnerability to dictionary attacks

Engineering Contradiction:
Improveuser convenienceVSAvoidsecurity
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent creates transformed copies of biometric templates that preserve the essential metric relationships while obscuring the original data. These transformed copies can be stored and compared without exposing the actual biometric information, providing security comparable to biometrics while maintaining the simplicity of automated authentication.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP3834108B1Securing sensitive data using distance-preserving transformations
Publication Date: 2023.04.05 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3834108B1 patent drawingFigure 1
  • EP3834108B1 patent drawingFigure 2~3
  • EP3834108B1 patent drawingFigure 4

AI summary

Disclosed in some examples are methods, systems, devices, and machine-readable mediums for securing biometric data using distance-preserving transformations. A distance-preserving transformation is a function which maps elements to the same or another metric space such that the distance between the elements in the new metric space is equal to the distance between the elements in the original metric space.