A Local Differential Privacy Preservation Method for High-dimensional Data Based on Big Data Mining

Conventional local differential privacy protection methods for high-dimensional data mainly use ConvLSTM (Convolutional Long Short-Term Memory) network to process data time series, which is vulnerable to user gradient update, resulting in poor protection performance indicators. Therefore, a local differential privacy protection method for high-dimensional data based on big data mining is proposed. That is to extract the local differential privacy protection features of high-dimensional data, and use big data mining to design high-dimensional data local differential privacy protection algorithm, thus completing high-dimensional data local differential privacy protection. The experimental results show that the designed data local differential privacy protection method has good protection indicators, reliability and certain application value, and has made certain contributions to solving the problem of data abuse and disclosure and ensuring the security rights and interests of users.