Optimal Key Generation for Privacy Preservation in Big Data Applications Based on the Marine Predator Whale Optimization Algorithm

Abstract

In the era of big data, preserving data privacy has become paramount due to the sheer volume and sensitivity of the information being processed. This research is dedicated to safeguarding data privacy through a novel data sanitization approach centered on optimal key generation. Due to the size and complexity of the big data applications, managing big data with reduced risk and high privacyposes challenges. Many standard privacy-preserving mechanisms are introduced to maintain the volume and velocity of big data since it consists of massive and complex data. To solve this issue, this research developed a data sanitization technique for optimal key generation to preserve the privacy of the sensitive data. The sensitive data is initially identified by the quasi-identifiers and the identified sensitive data is preserved by generating an optimal key using the proposed marine predator whale optimization (MPWO) algorithm. The proposed algorithm is developed by the hybridization of the characteristics of foraging behaviors of the marine predators and the whales are hybridized to determine the optimal key. The optimal key generated using the MPWO algorithm effectively preserves the privacy of the data. The efficiency of the research is proved by measuring the metrics equivalent class size metric values of 0.03, 185.07, and 0.04 for attribute disclosure attack, identity disclosure attack, and identity disclosure attack. Similarly, the Discernibility metrics value is measured as 0.08, 123.38, 0.09 with attribute disclosure attack, identity disclosure attack, identity disclosure attack, and the Normalized certainty penalty is measured as 0.002, 61.69, 0.001 attribute disclosure attack, identity disclosure attack, identity disclosure attack.