A Novel Chaotic based Privacy preserving machine learning model on large distributed client applications

With the rapid growth of data size, data storage and computational memory, it is essential to implement an advanced privacy preserving model on large datasets. Machine learning framework is used to extract essential hidden patterns which are plain text format for decision making in distributed applications. Privacy preserving data mining (PPDM) has emerged as an essential area for data confidential in terms of data exchange, decision making and data publication. Privacy preserving is a popular data privacy model for securing individual decision patterns from unauthorized access. As the decision-making patterns of the data owner are stored and distributed publicly, it leads to the misuse of information in distributed applications. Some privacy information about business organizations, industries and individuals has to be encoded before it is publicly shared or published. In this paper, a novel chaotic privacy preserving model is designed and implemented on the large distributed data for privacy preserving. Here, different traditional privacy preserving models are used to compare the proposed model to the traditional models.