The finger vein features have received extensive attention due to their high safety and stability characteristics, and are gradually being used in various fields. However, studies have shown that finger vein recognition systems based on convolutional neural networks are at huge security risks. Criminals can obtain part of the user information of the system through certain illegal operations on the recognition results or the system database stored in the recognition system, which puts the original vein data at huge security risks. Once compromised, the user information stored in the system will be permanently leaked, and the individual’s vein features will no longer be safe. In order to solve these problems, we propose a new finger vein image encryption scheme, which applies Rivest–Shamir–Adleman encryption technology to finger vein image encryption. In addition, a complete cancelable finger vein recognition system with template protection is proposed to ensure the security of the user’s vein template while maintaining the recognition performance. A set of rigorous comparative experiments and security analyses have been performed on four open databases. The experimental results show that the performance of our proposed encryption scheme and the entire system for the finger veins recognition and protection is reliable and efficient.

指静脉特征因其安全性和稳定性高的特点受到广泛关注，并逐渐应用于各个领域。然而，研究表明，基于卷积神经网络的指静脉识别系统存在巨大的安全风险。犯罪分子可以通过对识别结果或识别系统中存储的系统数据库进行某些非法操作，获取系统的部分用户信息，使原始静脉数据面临巨大的安全风险。一旦泄露，系统中存储的用户信息将永久泄露，个人的静脉特征将不再安全。为了解决这些问题，我们提出了一种新的手指静脉图像加密方案，将 Rivest-Shamir-Adleman 加密技术应用于手指静脉图像加密。此外，提出了一套完整的具有模板保护的可取消手指静脉识别系统，在保证识别性能的同时保证用户静脉模板的安全。对四个开放数据库进行了一系列严格的比较实验和安全分析。实验结果表明，我们提出的加密方案和整个手指静脉识别和保护系统的性能是可靠和高效的。对四个开放数据库进行了一系列严格的比较实验和安全分析。实验结果表明，我们提出的加密方案和整个手指静脉识别和保护系统的性能是可靠和高效的。对四个开放数据库进行了一系列严格的比较实验和安全分析。实验结果表明，我们提出的加密方案和整个手指静脉识别和保护系统的性能是可靠和高效的。