In this paper, we have surveyed the latest establishment in the field of privacy-preserving big data analytics. We have provided an extensive and structured reportage of collective big data analytics and privacy-preserving strategy before introducing a novel taxonomy of privacy-preserving big data analytics integrate with inspiring privacy scenarios in the big data factor. We explicitly focus on three main privacy-preserving data analytics problems including data publishing, data querying, and data mining. The proposed taxonomy is anticipate to give a systematic and multi-dimensional view of emerging topics in the field. In spite of recent years both industry and academia have put a lot of efforts into privacy-preserving big data analytics, this field is still indisputable demanding and it leaves a room for improving the existing schemes as well as developing new novel approaches with regard to an increase of performance and privacy level.

The generality of issue data sources and outsourced computing, the development of machine learning as service, collaborative learning have prompted cutting-edge solutions for privacy-related issues in the future.