In this project implement a machine learning strategy for smart edges using differential privacy. In existing system focus attention on privacy protection in training datasets in wireless big data scenario. Moreover, to guarantee privacy protection by adding Laplace mechanisms, and design two different algorithms Output Perturbation (OPP) and Objective Perturbation (OJP), which satisfy differential privacy. In addition, consider the privacy preserving issues presented in the existing literatures for differential privacy in the correlated datasets, and further provided differential privacy preserving methods for correlated datasets, guaranteeing privacy by theoretical deduction. This approach converts the original sample data sets into a group of Non-Sensitive data sets, from which the original samples cannot be reconstructed without the entire group of unreal data sets. Meanwhile, an accurate analysis can be built directly from those unreal data sets. This novel approach can be applied directly to the data storage as soon as the first sample is collected. The Relevant Columns Values Swapping approach is compatible with other privacy preserving approaches, such as without cryptography, for extra protection.