An Efficient Privacy-Preserving Palmprint Authentication Scheme Based on Homomorphic Encryption

In order to provide protection for biometric features in palmprint authentication, we propose a palmprint authentication scheme suitable for personal environments with privacy-preserving trait using the ElGamal encryption scheme which is mulplicatively homomorphic. To achieve faster running speed, we use binary vectors to represent palmprint features and use Hamming distance to indicate the similarity of different feature vectors. We give security and performance analysis, and use Matlab to implement some key modules of the proposed scheme. Theoretical analysis and experimental results show that the proposed scheme achieves confidential computations of palmprint feature vectors. The recognition accuracy can meet practical requirements and the overall performance transcends existing relative schemes.