It's necessary to keep sensitive data and private data safe. When financial information, healthcare information, and other sensitive consumer or user data are mishandled, they can be destructive. Due to a lack of access control over personal information, individuals may be susceptible to fraud and identity theft. This paper provides an overview of the ideas of data privacy, re-identification risk, and dataset utility, as well as the correlations between the three. On the adult dataset from the UCI Machine Learning Repository, this study presents a sensitivity analysis of the k-anonymization algorithm. ARX, an open-source anonymization tool, was used to show this.