Preserving Privacy in MapReduce Based Clouds: Insight into Frameworks and Approaches

The massive increase in computational power and data storage capacity provided by Cloud Computing as well as the vast amount of data generated each day have provided many organizations, businesses and authorities with more opportunities due to the advancement in data analysis and mining techniques. A serious problem is that Big Data includes sensitive user information that cannot be released to the cloud without proper protection because of multi-tenancy issues and threats. Privacy preservation of big data has been under intensive investigation with many different approaches proposed. In this paper, we focus on the research challenges of the privacy-preserving problem in the context of cloud computing and we survey existing solution approaches. Furthermore, a review of different existing MapReduce based frameworks will be presented and investigated against the research challenges identified in this paper.