An approach for enhancing data confidentiality in hadoop

Abstract

The quantity of prepared and stored data in the cloud is rising dramatically. The common storage devices at both hardware and software levels cannot satisfy the necessity of the cloud. This fact motivates the requirement for principles that can manage this difficulty. Hadoop is an expanded principle proposed to succeed in the big data challenge that usually utilizes MapReduce structure to prepare huge quantities of data of the cloud system. Hadoop has no policy to guarantee the protection and secrecy of the data collected in the hadoop distributed file system (HDFS). In the cloud, the security of sensitive data is a significant issue in which data encryption schemes play an avital rule. This research proposes a hybrid system between two popular asymmetric key cryptosystems (RSA, and ElGamal) to encrypt the data collected in HDFS. Thus before storing data in HDFS, the proposed cryptosystem is utilized to encrypt the data. The user of the cloud might upload data in two ways, non-safe or secure. The hybrid method presents more powerful computational complexity and less latency in comparison to the RSA cryptosystem alone.