Encrypted Biometric Matching With Liveness for One-to-Many Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional biometric systems face limitations in one-to-many searching, security vulnerabilities from faked or replayed biometric signals, and inefficiencies in managing encrypted biometric data, leading to compromised security and accuracy.
Innovation Solution
A privacy-enabled biometric system that performs one-to-many searches on encrypted biometric information using a hybrid authentication approach, combining distance metric and deep neural network (DNN) methods, with integrated liveness detection to ensure authenticity and privacy preservation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional biometric systems store and search unencrypted biometric data, then search speed and matching accuracy are improved, but security is compromised due to vulnerability to faked or replayed biometric signals
Solution Approach 1:
The patent introduces encrypted feature vectors as an intermediary representation that enables secure biometric matching without exposing raw biometric data. The encryption scheme allows polynomial-time one-to-many searching on encrypted data, resolving the contradiction by mediating between security requirements and search efficiency needs through a cryptographic layer that preserves computational functionality while protecting data confidentiality
Solution Approach 2:
The system transforms biometric data from raw form to encrypted feature vector form, changing the parameter representation while maintaining matching capability. This parameter transformation enables the system to operate in an encrypted domain where security is inherent, yet polynomial-time searching remains feasible through specialized cryptographic operations on the transformed data
2Reliability
If one-to-many biometric searching is implemented on encrypted biometric information, then security is improved, but computational complexity increases
Solution Approach 1:
The patent applies preliminary encryption transformation to convert biometric data into encrypted feature vectors before storage and searching operations. This preliminary action structures the data in a way that enables efficient polynomial-time one-to-many searching on encrypted data, reducing the computational complexity that would otherwise result from attempting to search encrypted biometric information directly
3Reliability
If liveness detection is integrated into the biometric authentication system, then security against spoofing is improved, but system complexity and processing time increase
Solution Approach 1:
The patent merges liveness detection functionality with the encrypted feature vector matching process, combining multiple security functions into a unified authentication pipeline. This merging approach integrates anti-spoofing verification with the core biometric matching operation, reducing overall system complexity compared to implementing separate liveness detection and authentication systems
Data Source
AI summary
A set of distance measurable encrypted feature vectors can be derived from any biometric data and/or physical or logical user behavioral data, and then using an associated deep neural network (“DNN”) on the output (i.e., biometric feature vector and/or behavioral feature vectors, etc.) an authentication system can determine matches or execute searches on encrypted data. Behavioral or biometric encrypted feature vectors can be stored and/or used in conjunction with respective classifications, or in subsequent comparisons without fear of compromising the original data. In various embodiments, the original behavioral and/or biometric data is discarded responsive to generating the encrypted vectors. In another embodiment, distance measurable or homomorphic encryption enables computations and comparisons on cypher-text without decryption of the encrypted feature vectors. Security of such privacy enabled embeddings can be increased by implementing an assurance factor (e.g., liveness) to establish a submitted credential has not been spoofed or faked.