Privacy-Preserving Biometric Authentication Using ECC Obfuscation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biometric authentication systems, such as relational hash and fuzzy vault approaches, are vulnerable to attacks like replay attacks and have limitations that make them unsuitable for widespread deployment, particularly due to proprietary nature and lack of error-tolerant set intersection for distance measurement of biometric features.
Innovation Solution
A set-based biometric authentication system that uses obfuscated feature point data and code words to create an enrollment biometric template, where the client module randomly selects code words from an Error Correction Code (ECC) to obfuscate feature points, ensuring that the authentication server cannot decode the un-obfuscated data, thus providing strong privacy guarantees.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional biometric authentication systems (relational hash, fuzzy vault) are used, then authentication functionality is provided, but the systems are vulnerable to replay attacks and lack strong privacy guarantees
Solution Approach 1:
The biometric template is segmented into multiple feature points, each associated with code words from an Error Correction Code. This segmentation allows the system to verify authentication without exposing individual biometric features, thereby preventing replay attacks while maintaining authentication security.
Solution Approach 2:
Error Correction Codes serve as an intermediary mechanism between the biometric feature points and the authentication verification. The code words obscure the actual biometric data, allowing the server to verify authentication without directly accessing or storing sensitive biometric information, thus providing privacy guarantees and resistance to replay attacks.
2Ease of operation
If biometric data is stored on the authentication server, then authentication verification is enabled, but the privacy of biometric data is compromised
Solution Approach 1:
The system extracts only the necessary verification information (code words and feature point relationships) from the complete biometric data, storing these on the server while keeping the actual biometric templates private on the client device. This extraction enables server-side verification without compromising the privacy of the full biometric information.
Solution Approach 2:
The biometric data is transformed from its original form into an obfuscated representation using Error Correction Codes. The server stores and processes these transformed parameters (code words and feature point associations) rather than the raw biometric data, enabling verification while preserving privacy through parameter transformation.
3Reliability
If error-tolerant set intersection is implemented for distance measurement, then robustness to biometric variation is improved, but existing systems lack this capability
Solution Approach 1:
Error Correction Codes are pre-generated and associated with each feature point during template creation. This preliminary encoding establishes the error-tolerant framework in advance, allowing the system to naturally handle biometric variations during authentication without requiring complex post-processing or additional adaptability mechanisms.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
A method includes extracting a set of enrollment feature points from an enrollment biometric measurement. The method also includes randomly selecting one or more enrollment code words from an error correction code. The method also includes determining obfuscated enrollment feature point data describing an obfuscated version of the set of feature points that is obfuscated using the one or more enrollment code words. The method also includes determining obfuscated enrollment code word data describing an obfuscated version of the one or more enrollment code words that is obfuscated using a random enrollment polynomial. The method also includes determining an enrollment biometric template including the obfuscated enrollment feature point data and the obfuscated enrollment code word data. The method also includes determining enrollment data including the enrollment biometric template. The enrollment data may be configured to keep the one or more enrollment code words and the random enrollment polynomial secret.