The invention belongs to the technical field of big data, and particularly relates to data desensitization in big data. A public data set is generated through a data generation network model to replace the original data set for query, so that real data in the original data set is prevented from being queried and accessed; and meanwhile, the distribution of the data in the public data set and the distribution of the data in the original data set are kept consistent, and the incidence relation between the data in the original data set is reserved.