Deep learning-based biometric cryptographic key generation with post-quantum security

In contemporary digital security systems, the generation and management of cryptographic keys, such as passwords and pin codes, often rely on stochastic random processes and intricate mathematical transformations. While these keys ensure robust security, their storage and distribution necessitate sophisticated and costly mechanisms. This study explores an alternative approach that leverages biometric data for generating cryptographic keys, thereby eliminating the need for complex storage and distribution processes. The paper investigates biometric key generation technologies based on deep learning models, specifically utilizing convolutional neural networks to extract biometric features from human facial images. Subsequently, code-based cryptographic extractors are employed to process the primary extracted features. The performance of various deep learning models and the extractor is evaluated by considering Type 1 and Type 2 errors. The optimized algorithm parameters yield an error rate of less than 10%, rendering the generated keys suitable for biometric authentication. Additionally, this study demonstrates that the application of code-based cryptographic extractors provides a post-quantum level of security, further enhancing the practicality and effectiveness of biometric key generation technologies in modern information security systems. This research contributes to the ongoing efforts towards secure, efficient, and user-friendly authentication and encryption methods, harnessing the power of biometric data and deep learning techniques.