Big Data is an emerging area and concerns managing datasets whose size is beyond the ability of commonly used software tools to capture, process, and perform analyses in a timely way. The Big Data software market is growing at 32% CAR, almost four times more than the whole ICT market, and the quantity of data to be analyzed is expected to double every two years. Security and privacy are becoming very urgent Big Data aspects that need to be tackled. Indeed, users share more and more personal data and user generated content through their mobile devices and computers to social networks and cloud services, losing data and content control with a serious impact on their own privacy. Privacy is one area that had a serious debate recently, and many governments require to data providers and companies to protect the users' sensitive data. To mitigate these problems, many solutions have been developed to provide data privacy, which, however, introduce some computational overhead when data is processed. The goal of this paper is to quantitatively evaluate the performance and cost impact of multiple privacy protection mechanisms. A real industry case study concerning tax fraud detection has been considered. Many experiments have been performed to analyze the performance degradation and additional cost (required to provide a given service level) for running applications in a cloud system.