A Survey: Privacy Preservation in Data Publishing

Many organizations like small and medium business (SMB), the datasets are being actively collected and stored by businesses. The majority of them have acknowledged the potential significance of this data as a source of information for corporate decision-making. Privacy preservation in data publishing is required to protecting sensitive information. There are several ways that the personal data might be utilized improperly. This study presents a brief overview of a number of strategies, including generalization and bucketization, both of which have been developed for privacy preservation in micro data publishing. Recent research has demonstrated that generalizing to high-dimensional data will result in significant information loss, and bucketization doesn't prevent membership disclosure, so it can't be applied to data where there isn't a distinct distinction between sensitive and quasi-identifying attributes. The generalization and bucketization approaches for anonymization are designed to protect your privacy when creating micro data. These methods can be applied to privacy preservation in data publishing. Also, we look at a game theory model and compare the RSA and ECC algorithm.