Cancelable Biometrics via Random Projection Transforms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biometric systems lack effective methods for producing cancelable and revocable biometrics, as traditional techniques face challenges with key management, computation overhead, and scalability, while also compromising data privacy and utility.
Innovation Solution
The use of random projection transforms provides a one-way irreversible transformation of biometric data, allowing for secure authentication and revocation of compromised data through incoherent random projections, leveraging Slepian-Wolf coding principles for distributed compression and reconstruction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If encryption techniques are used to produce cancelable biometrics, then security and revocability are improved, but key management complexity and computation overhead increase
Solution Approach 1:
The patent extracts the security function from complex encryption key management by using a public authentication code that can be freely distributed. The secret key is eliminated from the system architecture, replacing it with a public code that serves the authentication function without requiring secure key storage or distribution mechanisms.
Solution Approach 2:
The patent introduces an intermediary authentication code that mediates between the biometric data and the verification process. This public code acts as a mediator that can be openly shared while still providing security, eliminating the need for secret key management while maintaining authentication reliability.
2Reliability
If distorting transformations are applied to biometric data, then revocability is improved, but data privacy and utility may be compromised
Solution Approach 1:
The patent creates a public copy of the authentication code that can be freely distributed and used for verification. This copying approach allows the authentication function to be performed without restricting access to the code, while the underlying biometric data remains protected and can be revoked by generating new authentication codes.
Solution Approach 2:
The patent changes the parameter of the authentication code from secret to public, fundamentally altering how authentication works. Instead of relying on secret transformations that may compromise data utility, the system uses public codes with changing parameters that maintain both privacy and revocability.
3Adaptability or versatility
If multiple transformed biometric versions are stored for different applications, then adaptability is improved, but storage requirements and system complexity increase
Solution Approach 1:
The patent creates a universal public authentication code that can serve multiple applications and purposes. Instead of storing different transformed biometric versions for each application, a single public code can be used across multiple contexts, providing adaptability without increasing storage requirements or system complexity.
Data Source
Figure 1~2
Figure 3~6
Figure 4~5
AI summary
To provide cancelable biometrics, random projection transforms are used to produce transformed biometric data that may be used for authentication purposes. Each random projection transform provides a one-way or irreversible transformation such that the resulting transformed biometric data alone cannot be used to reconstruct the biometric data. Enrollment and backup transforms are produced based on enrollment biometric data. Authentication is possible by similarly transforming authentication biometric and then securely reconstructing the enrollment and authentication biometric data for comparison. In a similar manner, the enrollment and backup transforms may be used to reenroll biometric data when its corresponding transformed biometric data is compromised without requiring further user intervention.