Blockchain is the technology on the basis of the recent smart and digital contracts. It ensures at this system the required characteristics to be effectively applied. In this work, we propose a novel encryption scheme specifically built to authorize and sign transactions in digital or smart contracts. The face is used as a biometric key, encoded through the Convolutional Neural Network (CNN), FaceNet. Then, this encoding is fused with an RSA key by using the Hybrid Information Fusion algorithm (BNIF). The results show a combined key that ensures the identity of the user that is executing the transaction by preserving privacy. Experiments reveal that, even in strong heterogeneous acquisition conditions for the biometric trait, the identity of the user is ensured and the contract is properly signed in less than 1.86 s. The proposed ECB2 encryption scheme is also very fast in the user template creation (0.05s) and requires at most four attempts to recognize the user with an accuracy of 94%.

区块链是基于最近的智能和数字合约的技术。它确保在该系统上有效地应用所需的特性。在这项工作中，我们提出了一种新颖的加密方案，专门用于授权和签署数字或智能合约中的交易。脸部用作生物特征识别密钥，通过FaceNet卷积神经网络（CNN）进行编码。然后，通过使用混合信息融合算法（BNIF），将此编码与RSA密钥融合。结果显示了一个组合密钥，该组合密钥通过保留隐私来确保正在执行交易的用户的身份。实验表明，即使在强大的生物特征异质获取条件下，也可以确保用户的身份，并且可以在不到1.86 s的时间内正确签署合同。