A differentially private space decomposition method and system

Abstract

A method for difference privacy space decomposition is disclosed, including: obtaining the d-dimensional point dataset, generating a complete domain omega for constructing a beta tree from the d-dimensional point data set, and a point count cnt in the complete domain omega, and reading all of the Laplace noise data from a file that includes the Laplace noise, creating a beta tree of the d-dimensional point data set by using the resulting complete domain Omega, and the point count cnt in the complete domain omega, adding the product obtained by multiplying any one of the Laplacian noise data bythe noise figure to the point count of each leaf node of the created beta tree, wherein different Laplacian noise data are selected for different leaf nodes. The invention can solve the technical problems that the privacy of the intermediate node is easy to expose, the noise cost is high due to the inaccurate domain decomposition, and the depth of the spatial decomposition privacy tree is difficult to accurately determine, which exist in the prior differential privacy space decomposition method based on the Plath distribution.

Description

technical field [0001] The invention belongs to the technical field of privacy protection, and more particularly relates to a differential privacy space decomposition method and system. Background technique [0002] As a new privacy protection framework, differential privacy achieves the effect of privacy protection by adding appropriate noise to query or analysis results. [0003] In the process of differential privacy protection, based on security considerations, it is necessary to recursively decompose the entire domain into sub-domains to generate a hierarchical privacy tree, and add Laplacian noise to the point count of each node in the privacy tree. The process is called differentially private space decomposition. [0004] However, there are some non-negligible technical problems in the existing differential privacy space decomposition method based on Laplacian distribution: First, since the Laplacian distribution is symmetric to the origin, in the space decomposition...

AI Technical Summary

Problems solved by technology

[0005] In view of the above defects or improvement needs of the prior art, the present invention provides a differential privacy space decomposition method and system, the purpose of which is to solve the privacy of intermediate nodes existing in the existing differential privacy space decomposition method based on Laplacian distribution Technical problems such as easy exposure, high noise cost due to inaccurate regional decomposition, and difficulty in accurately determining the depth of the spatially decomposed privacy tree

Images