Department of Computer Science
Differentially Private High-Dimensional Data Publication via Sampling-Based Inference
Releasing high-dimensional data enables a wide spectrum of data mining tasks. Yet, individual privacy has been a major obstacle to data sharing. In this paper, we consider the problem of releasing high-dimensional data with differential privacy guarantees. We propose a novel solution to preserve the joint distribution of a high-dimensional dataset. We first develop a robust sampling-based framework to systematically explore the dependencies among all attributes and subsequently build a dependency graph. This framework is coupled with a generic threshold mechanism to significantly improve accuracy. We then identify a set of marginal tables from the dependency graph to approximate the joint distribution based on the solid inference foundation of the junction tree algorithm while minimizing the resultant error. We prove that selecting the optimal marginals with the goal of minimizing error is NP-hard and, thus, design an approximation algorithm using an integer programming relaxation and the constrained concave-convex procedure. Extensive experiments on real datasets demonstrate that our solution substantially outperforms the state-of-the-art competitors.
Source Publication Title
Proceeding KDD 15 Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Place of Publication
Sydney, NSW, Australia
Link to Publisher's Edition
Chen, Rui Chen, Qian Xiao, Yu Zhang, and Jianliang Xu. "Differentially Private High-Dimensional Data Publication via Sampling-Based Inference." Proceeding KDD 15 Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2015): 129-138.