Biometric Authentication Using Independent Feature Point Transformation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biometric authentication systems using fingerprint templates face challenges in protecting user privacy and security due to the limited number of fingerprints per user, difficulty in changing templates, and vulnerability to leakage and brute force attacks, especially when the same biometric information is used across different systems.
Innovation Solution
The method involves independently transforming and verifying feature points of fingerprints using a transformation parameter, which is kept secret, allowing for secure and privacy-protected authentication by regenerating and re-registering templates with changed parameters across different systems, and applying the transformation parameter to each feature point independently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the template is encrypted and stored, then the security against unauthorized access is improved, but the system becomes vulnerable to leakage caused by sophisticated attacks and intentional actions by server administrators
Solution Approach 1:
The patent extracts the secret parameter from the server side and places it on the client side. The server only stores the transformed feature quantity without the secret parameter, so even if the server database is compromised, the transformed data cannot be reversed to obtain the original biometric information or the secret parameter.
Solution Approach 2:
Instead of the server holding and managing the secret key/parameter as in traditional encryption, the patent inverts the architecture by having the client hold the secret parameter locally. This reversal eliminates the server's ability to accidentally or intentionally leak the secret, as the server never possesses it.
2Ease of operation
If the same biometric information is used across different systems, then the convenience for users is improved, but the security is reduced if one template is leaked
Solution Approach 1:
The patent applies different local transformations (different secret parameters) to the same biometric feature quantity for different systems. Each system receives a locally adapted transformed version that is specific to that system's secret parameter, making leaked transformed data from one system useless for attacking other systems.
Solution Approach 2:
The patent changes the transformation parameters (secret values) for each system or application. The same original biometric feature quantity is transformed using different parameters for different systems, creating unique transformed representations that cannot be cross-referenced or attacked using data from other systems.
3Reliability
If block substitution transformation is used, then the cancelable biometric authentication is realized, but the authentication accuracy degrades when feature points are displaced beyond block boundaries
Solution Approach 1:
The patent segments the feature quantity into multiple individual feature points, each transformed independently using the secret parameter. This segmentation allows each feature point to be processed separately, maintaining the ability to match features even when there is displacement or distortion, as long as the relative relationships are preserved.
4Reliability
If the transformation parameter is kept secret by the client, then the privacy protection is improved, but the degree of freedom of the transformation parameter is limited
Solution Approach 1:
The patent moves the secret parameter management to a different dimension - from server-side centralized management to client-side decentralized management. This dimensional change allows the system to maintain strong privacy protection while enabling greater flexibility, as each client can independently manage their own secret parameter without server intervention.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Upon registration, a client extracts plural feature points and information (identification information) by which each of the feature points can be identified, from a user's fingerprint, and randomly generates a transformation parameter for each feature point to transform the coordinates and direction. The transformed identification information (template) is transmitted to an authentication server and stored in a,memory. The identification information and transformation parameters of the feature points are stored in a memory medium of the user. Upon authentication of the user, the client extracts feature points from the user' s fingerprint, and identifies the feature points by the identification information in the memory medium. The client transforms the identified feature points by reading the corresponding transformation parameters from the memory medium, and transmits the transformed information to the authentication server. The server verifies the received identification information against the template registered in advance, to authenticate the user.