Homomorphic Biometric Matching for Secure One-to-Many Authentication
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 in identity validation.
Innovation Solution
A privacy-enabled biometric system utilizing encrypted feature vectors and deep neural networks (DNNs) for secure, scalable one-to-many matching, incorporating liveness detection and randomized biometric checks to authenticate identities, ensuring secure and accurate authentication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional biometric systems perform one-to-many searching, then identity validation capability is improved, but security is worsened due to vulnerability to faked or replayed biometric signals
Solution Approach 1:
The patent introduces homomorphic encryption as an intermediary layer that enables biometric matching operations on encrypted data without decryption. This mediator allows the system to perform one-to-many searching while maintaining security, as the encrypted biometric templates cannot be directly manipulated or replayed by attackers. The homomorphic encryption scheme enables computational operations on ciphertexts, preserving both versatility and reliability.
Solution Approach 2:
The system transforms biometric data from plaintext to encrypted form using homomorphic encryption, changing the parameter state of the data. This transformation allows the system to maintain functional capabilities (one-to-many searching) while improving security properties, as the encrypted representations prevent replay attacks and faked signal exploitation.
2Reliability
If biometric data is encrypted for security, then security is improved, but processing efficiency and search capability are worsened
Solution Approach 1:
The patent replaces traditional mechanical decryption-and-process workflows with homomorphic encryption-based computational operations. Instead of decrypting data for processing (which creates security vulnerabilities and inefficiency), the system performs matching operations directly on encrypted biometric templates, substituting the mechanical decryption step with cryptographic computation that maintains both security and efficiency.
Solution Approach 2:
Homomorphic encryption serves as an intermediary that enables efficient processing of encrypted data. The cryptographic system allows the processor to perform matching operations on encrypted biometric templates without decryption, maintaining security while preserving processing efficiency through optimized cryptographic operations.
3Speed
If conventional systems use unencrypted biometric data for processing, then processing speed is improved, but security and privacy are worsened
Solution Approach 1:
The system changes the cryptographic parameter state of biometric data from plaintext to homomorphically encrypted form, enabling processing operations that maintain both speed and security. The homomorphic encryption scheme is designed to allow efficient computational operations on ciphertexts, achieving processing speed comparable to plaintext operations while simultaneously improving security and privacy.
4Adaptability or versatility
If one-to-many biometric searching is implemented, then authentication versatility is improved, but computational complexity and time requirements are worsened
Solution Approach 1:
The patent replaces traditional sequential comparison methods with homomorphic encryption-based batch processing capabilities. The system can perform multiple biometric matching operations simultaneously on encrypted data, substituting time-consuming sequential searches with parallelizable cryptographic operations that reduce overall search time while maintaining authentication versatility.
Data Source
AI summary
In one embodiment, a set of feature vectors can be derived from any biometric data, and then using a deep neural network (“DNN”) on those one-way homomorphic encryptions (i.e., each biometrics' feature vector) an authentication system can determine matches or execute searches on encrypted data. Each biometrics' feature vector can then be stored and/or used in conjunction with respective classifications, for use in subsequent comparisons without fear of compromising the original biometric data. In various embodiments, the original biometric data is discarded responsive to generating the encrypted values. In another embodiment, the homomorphic encryption enables computations and comparisons on cypher text without decryption of the encrypted feature vectors. Security of such privacy enable biometrics can be increased by implementing an assurance factor (e.g., liveness) to establish a submitted biometric has not been spoofed or faked.