Efficient Logistic Regression with Local Differential Privacy

Internet of Things devices are expanding rapidly and generating huge amount of data. There is an increasing need to explore data collected from these devices. Collaborative learning provides a strategic solution for the Internet of Things settings but also raises public concern over data privacy. In recent years, large amount of privacy preserving techniques have been developed based on differential privacy and secure multi-party computation. A major challenge of collaborative learning is to balance disclosure risk and data utility while maintaining high computation efficiency. In this paper, we proposed privacy preserving logistic regression model using matrix encryption approach. The secure scheme achieves local differential privacy and can be implemented for both vertical and horizontal partitioning scenarios. Moreover, cross validation is investigated to generate robust model results without increasing the communication cost. Simulation illustrates the high efficiency of proposed scheme to analyze dataset with millions of records. Experimental evaluations further demonstrate high model accuracy while achieving privacy protection.