一种新的基于指纹与人脸特征级融合的模糊金库方案  

A novel fuzzy vault scheme based on the feature level fusion of fingerprint and face features

作　　者：李洵 游林[1] 梁家豪 颜春辉 LI Xun, YOU Lin, LIANG Jiahao, YAN Chunhui(College of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, China)

机构地区：[1]杭州电子科技大学通信工程学院,浙江杭州310018

出　　处：《电信科学》2018年第10期72-84,共13页Telecommunications Science

摘　　要：针对基于生物特征的模糊金库易受相关攻击导致密钥和生物特征模板丢失以及基于单生物特征的模糊金库的认证性能不可靠的问题,提出了一种新的基于指纹与人脸特征级融合的模糊金库方案。该方案对指纹特征与人脸特征分别进行不可逆变换,并基于Diffie-Hellman算法在特征级变换后将指纹与人脸特征融合为一个模板。最后,将所得的融合模板用来构建模糊金库,通过更新随机矩阵使金库具备可撤销特性,有效抵御相关攻击,实现可靠的身份认证。实验结果表明,本文方案提高了系统的可靠性和多生物特征模板的安全性。Aiming at the problem that the biometric feature-based fuzzy vault is vulnerable to correlation attack and the loss of key and biometric template, and the authentication performance of fuzzy vault based on single biometric feature is unreliable, a novel fuzzy vault scheme based on the feature level fusion of fingerprint and face features was proposed. This scheme carried out irreversible transformation of fingerprint features and face features, and based on the Diffie-Hellman algorithm, the transformed fingerprints and face features were fused into a template at the feature level. Finally, the fusion template was used to construct the fuzzy vault. By updating the random matrix, the vault could be revoked, which could effectively resist the correlation attacks and achieve reliable authentication. Experimental results show that the proposed scheme improves the reliability of the system and the security of multiple biometric templates.

关 键 词：模糊金库 指纹特征 人脸特征 模板保护 身份认证 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]