Big data usually running in large-scale and centralized key management systems. However, the centralized key management systems are increasing the problems such as single point of failure, exchanging a secret key over insecure channels, third-party query, and key escrow problem. To avoid these problems, we propose an improved certificate-based encryption scheme that ensures data confidentiality by combining symmetric and asymmetric cryptography schemes. The combination can be implemented by using the Advanced Encryption Standard (AES) and Elliptic Curve Diffie-Hellman (ECDH). The proposed scheme is an enhanced version of the Certificate-Based Encryption (CBE) scheme and preserves all its advantages. However, the key generation process in our scheme has been done without any intervention from the certificate issuer and avoiding the risk of compromised CA. The Elliptic Curve Digital Signature Algorithm (ECDSA) has been used with the ECDH to handle the authentication of the key exchange. The proposed scheme is demonstrated on a big dataset of social networks. The scheme is analyzed based on security criteria that have been compared with the previous schemes to evaluate its performance.
