Low latency and secure data encryption for multi-hop biometric authentication in distributed networks

Abstract

Because of the rapid development of artificial intelligence and big data technology, biometric information has become widely used in applications across industries, such as biometric authentication and telemedicine. However, biometric information is unique and cannot be changed or restored once leaked. Therefore, the security and management of biometric information must be more thorough than those applied to other types of information. In particular, if end-to-end encryption is not maintained and decryption is performed for the sake of precise data learning or information protection at intermediate nodes, the security of the process becomes weaker, increasing the risk of data leakage. To solve such problems, research is currently being conducted on homomorphic encryption, in which calculation and learning can be performed in an encrypted state, for biometric recognition systems. However, homomorphic encryption requires a larger ciphertext size than those used in other encryption methods. Thus, this type of encryption has been limited by its large delay, which deteriorates the performance because of noise boost-up and thus does not guarantee quality of service in a multi-hop network environment. This study proposes a novel multi-hop encryption-based biometric information slicing method to improve latency and security in biometric authentication. Experimental results demonstrate an 83.23% latency reduction compared to a conventional single-process model in a Paillier-based homomorphic encryption environment. Additionally, it offers a 98.4% security improvement compared to the commonly used Advanced Encryption Standard for packet encryption. This approach effectively addresses the trade-off between security and latency, a critical aspect not fully explored in previous studies.