Biometric Template Obfuscation via Interest Point Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Biometric templates used for authentication are vulnerable to security compromises as they are often stored in their original form, which can lead to exposure and unauthorized access.
Innovation Solution
A method and system for securing biometric templates by generating obfuscated templates using interest points and obfuscating data points, where the spatial distribution of these points is similar, and encoding keys using a subset of these points, ensuring that only a subset of points is required for verification, thus maintaining privacy and security.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If biometric templates are stored in their original form for authentication, then verification accuracy is maintained, but security is compromised due to exposure and unauthorized access risks
Solution Approach 1:
The biometric template is segmented into multiple components: interest points extracted from biometric imagery, obfuscating data points generated to mask the interest points, and a key derived from a subset of these points. This segmentation allows the template to be stored in a distributed, obfuscated form that maintains verification accuracy while preventing unauthorized reconstruction of the original biometric data.
Solution Approach 2:
Obfuscating data points serve as intermediaries between the interest points and the stored template. These data points are generated based on interest points but contain no direct information about the original biometric features. The obfuscating data points act as a protective layer that prevents reverse-engineering while allowing legitimate verification through the key derivation process.
2Object-affected harmful factors
If obfuscating data points are generated based on interest points with similar spatial distribution, then security is improved by making reverse-engineering difficult, but template complexity increases
Solution Approach 1:
The template undergoes parameter changes by transforming the original biometric data into a different representation space. Interest points are transformed into obfuscating data points with modified spatial relationships, and a key is derived from a subset of these transformed points. This parameter transformation increases reverse-engineering difficulty while maintaining a manageable template structure through selective point usage.
3Productivity
If a subset of points is used for key encoding and verification, then processing efficiency is improved, but information loss may occur
Solution Approach 1:
A key subset of points is extracted from the complete set of interest and obfuscating data points for key encoding and verification purposes. This extraction process selects only the necessary points required for authentication, improving verification efficiency by reducing the number of points that need to be processed while maintaining sufficient information for accurate authentication through the cryptographic key derivation.
Data Source
AI summary
Methods and systems for securing biometric templates and generating secret keys are provided. One or more images are received. Interest points are identified based on the received images, and a plurality of obfuscating data points are generated based on the interest points. An obfuscated template based on the interest points and the obfuscating data points is created and stored. A secret key can be encoded using a subset of at least one of the obfuscating data points and the interest points in the template.