Efficient and verifiable keyword search over public-key ciphertexts based on blockchain

Abstract

Public-key encryption with keyword search (PEKS) is a powerful cryptographic primitive that enables a receiver to search keywords over ciphertexts hosted on an honest-but-curious server in the asymmetric-key setting while hiding the keywords from the server. Many researchers have devoted their efforts to achieving expressive search, security against keyword guessing attacks, and efficient search performance. However, until now, no effective PEKS scheme can achieve verifiable search completeness in the standard PEKS security model. In practice, the server may intentionally or unintentionally lose the receivers’ data. Hence, verifiable search completeness is essential for receivers to audit the service quality of the server. To address this problem, this work develops a blockchain-based PEKS framework. This framework only utilizes the distributed ledger role of the blockchain, making it general. Additionally, we find that existing PEKS schemes cannot be efficiently deployed into the framework due to the inefficient use of randomness, which increases the ciphertext sizes. To tackle this problem, we utilize randomness reuse technique to propose a novel PEKS scheme. The proposed scheme achieves linear search complexity with respect to the total number of files in the dataset. To demonstrate the efficiency of our scheme, we perform comprehensive experiments to evaluate it and three other state-of-the-art schemes. The experimental results show that our PEKS scheme is superior to existing PEKS schemes in both the encryption and search phases and significantly reduces the sizes of generated ciphertexts.