Biometric Template Protection via XOR Codeword Encoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric security systems face challenges in securely storing and managing biometric reference data, as it is difficult to change or recover in case of loss, leading to security vulnerabilities.
Innovation Solution
A method involving quantization of feature components from biometric samples, assigning data bit sequences with specific Hamming distances, concatenating these into bit strings, and using an exclusive disjunction (XOR) operation with helper data to create a codeword for secure identity verification, incorporating error-correcting codes for robustness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If biometric reference data is stored in the system for comparison, then identity verification capability is improved, but security risk increases due to potential loss or compromise of the biometric data
Solution Approach 1:
The patent extracts only the necessary verification capability from the biometric data by using helper data and error-correcting codes. The actual biometric template is not stored in the database; instead, only helper data that enables verification is stored, thereby removing the security risk associated with storing complete biometric references while maintaining verification reliability
Solution Approach 2:
The patent introduces helper data as an intermediary between the biometric sample and the verification process. This helper data, combined with error-correcting codes, acts as a mediator that enables identity verification without requiring storage of the actual biometric template, thus resolving the contradiction between verification capability and security risk
2Measurement precision
If error-correcting codes are used to decode codewords, then measurement error tolerance is improved, but system complexity increases
Solution Approach 1:
The patent applies error-correcting codes during the enrollment phase to pre-process the biometric data and create helper data with built-in error correction capability. This preliminary action ensures that when verification occurs, the system can tolerate measurement errors without requiring complex real-time correction mechanisms, thus improving error tolerance while keeping verification complexity manageable
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This invention relates to methods and devices for verifying the identity of a person based on a sequence of feature components extracted from a biometric sample. Thereafter, the feature components are quantized and assigned a data bit sequence in such a way that adjacent quantization intervals have a Hamming distance of 1. The data bit sequences are concatenated into a bit string, and said bit string is combined with a helper data set by using an exclusive disjunction (XOR) operation into a codeword. Finally, the codeword is decoded into a secret V and a secret S is matched with the secret V.