Multi-core Approach towards Efficient Biometric Cryptosystems

Charles McGuffey, Chen Liu

Abstract: Protecting data is a critical part of life in the modern world. The science of protecting data, known as cryptography, makes use of secret keys to encrypt data in a format that is not easily decipherable. However, most modern cryptography systems use passwords to perform user authentication. These passwords are a weak link in the security chain, and are a common point of attack on cryptography schemes. One alternative to password usage is biometrics: using a person's physical characteristics to verify whom the person is and unlock the data correspondingly. This study focuses on the Cambridge biometric cryptosystem, a system for performing user authentication based on a user's iris data. We converted our implementation of this algorithm from a single-core system to a system that can run on multiple cores. The experiment takes place on an Intel Single Chip Cloud Computer (SCC), an experimental processor created by Intel Labs. A design pattern has been created for the parallelization of software functions using multiple cores. Using this design pattern, two functions in the system were accelerated. The system generated by this acceleration process produced limited computational speedup, but provided results that can be applied to a variety of hardware acceleration problems.