Privacy-Preserving and Information-Sharing Mechanisms Using Marine Fish Optimization for Big Data Applications

Big data refers to extensive, intricate, and expanding datasets that originate from various independent sources. In recent years, big data has attracted significant attention as it has the potential to generate new insights that foster technological innovation and drive economic development. Consequently, researchers have started to focus their efforts on processing big data to address the challenges associated with its high volume, velocity, and variety, commonly referred to as the “3Vs.” In addition to the 3V challenges, new privacy and security concerns are emerging within the realm of big data. Techniques for data mining are utilized to extract beneficial knowledge from large amounts of data, also referred to as big data. Many data mining methods exist that can assist in finding valuable knowledge from complex relationships within big data, as well as from dynamically changing volumes, especially when the amount of data tends to shift rapidly. Preserving the privacy and integrity of private and public data shared by different entities in a big data framework is a major concern. This research proposes a model for preserving privacy in data sharing within the big data framework, known as Marine Fish Optimization (MFO)-Privacy Preservation. MFO is a hybrid approach that combines the behaviors of both marine predators and jellyfish. The optimization within this model includes a privacy key optimizer based on the behavioral principles of marine predators and jellyfish. The algorithm generates keys to modify data clusters to improve data privacy while maintaining data integrity and usability. This hybrid approach (MFO) addresses complex optimization challenges. Based on the results, MFO achieved a data privacy rating of 1.869, with a decryption time of 0.02249 and an encryption time of 0.329.