AN ENHANCED PRIVACY PRESERVING APPROACH WITH ENFORCING POLICIES FOR PROCESSING BIG DATA IN SPARK FRAMEWORK

Abstract

Ensuring the privacy for the big data stored in a cloud system is one of the demanding and critical process in recent days. Generally, the big data contains a huge amount of data, which requires some security measures and rules for assuring the confidentiality. For this reason, different techniques have been developed in the traditional works, which intends to guarantee the privacy of the big data by implementing key generation, encryption, and anonymization mechanisms. But, it limits the issues of increased time consumption, computational complexity, and error rate. Thus, the proposed work aims to design an enhanced mechanism for a secure big data storage. Here, the user’s bank dataset is considered as the input, which is protected from the unauthorized users by guaranteeing both the privacy and secrecy of the data. Here, the raw dataset is preprocessed to increase the data quality and correctness. Then, the security policies (i.e. rules) are generated for allowing the restricted access on the data by using an Improved FP-Growth (IFP-G) algorithm. Consequently, the sensitive and non-sensitive data attributes are classified based on the extracted features by using an Enhanced Random Forest (ERF) classification technique. At last, the privacy of user’s personal information and other details are protected with the use of a Modified Incognito Anonymization based Privacy Preservation (MIA-PP) algorithm. These enhanced mechanisms guarantee the security and confidentiality of the big data with reduced time consumption and increased accuracy. During experimental evaluation, the results of the proposed privacy mechanism is analyzed and compared by using different measures. Also, some of the existing anonymization and classification techniques have been considered to prove the betterment of the proposed technique.