Abstrato

A Combined Robust Hashing and Secure Sketch Algorithm for Multi-Biometric Template Security

Ms. E.Durgadevi, Mrs. B.Karthiga, Mrs. B.Revathi, Ms. M.Revath

Multi-Biometric template security has become a very important issue in biometric authentication systems. If once a biometric template is compromised, it leads to serious security issues and privacy threats because unlike passwords, it is not possible for an authorized user to revoke his biometric identifiers and switch to another set of uncompromised identifiers. When using unimodal biometric systems (i.e., single Biometric Template) it leads to a variety of problems such as noisy data, intra-class variations, restricted degrees of freedom, non-universality, spoof attacks, unacceptable error rates, minimum key strength and so on. Some of these limitations can be resolved by deploying Multimodal Biometric systems that integrates the multiple sources of information at various processing stages. In a Multimodal Biometric system each template is processed independently and then fusion technique is applied to combine these templates at anyone of the stage. The input templates that have taken are face, iris and voice. Here, in the proposed work Biometric fusion is applied at the feature level to combine the features of those templates. And then, secure sketch, a recently proposed error-tolerant cryptographic primitive is applied to the biometric template. After that, to improve the key strength of the Sketch, Robust Hashing is applied. The Entropy of the key is measured, which measures the key strength. The FAR and FRR rates are also used to determine the key strength.