Implementation and evaluation of fuzzy vault on real applications of biometric authentication

Abstract

Many applications handle confidential information from their users. These information need to be handled in a secure way. One way of handling information securely is through cryptography. Usual cryptosystems are secure, but they have the hardness of cryptography keys handling. One way to protect these cryptography keys is through authentication mechanisms and the most common authentication mechanism is usage of passwords. However, the usage of passwords is weakest link on a conventional cryptosystem, because passwords can be easily copied or stolen. The usage of biometrics is a way to overcome issues regarded the usage of passwords. Biometrics uses physiologic or behavioral features of people to identify them. Thus, the usage of biometrics is better than passwords, since it is harder to copy or stole a biometric signal than a password. Biometric signals are more secure, but they also need to be protected. One way to protect biometric signals with other information is to use cryptography based on biometric keys. But, by the variability of the biometric signal, biometrics cannot be used as cryptographic keys of a traditional cryptosystem. Cryptosystems that address to overcome these issues are called biometric cryptosystems. This project implements the biometric cryptosystem called Fuzzy Vault in an application scenario to evaluate the behavior of this cryptosystem in real situations. (AU)