dpart: Differentially Private Autoregressive Tabular, a General Framework for Synthetic Data Generation
This provides a flexible and scalable tool for users ranging from beginners to experts in synthetic data generation, addressing privacy concerns in data sharing.
The authors introduced dpart, a general framework for generating differentially private synthetic data using autoregressive modeling, which supports various methods like machine learning models and histograms, and includes specific instances such as an optimized PrivBayes and a new dp-synthpop model.
We propose a general, flexible, and scalable framework dpart, an open source Python library for differentially private synthetic data generation. Central to the approach is autoregressive modelling -- breaking the joint data distribution to a sequence of lower-dimensional conditional distributions, captured by various methods such as machine learning models (logistic/linear regression, decision trees, etc.), simple histogram counts, or custom techniques. The library has been created with a view to serve as a quick and accessible baseline as well as to accommodate a wide audience of users, from those making their first steps in synthetic data generation, to more experienced ones with domain expertise who can configure different aspects of the modelling and contribute new methods/mechanisms. Specific instances of dpart include Independent, an optimized version of PrivBayes, and a newly proposed model, dp-synthpop. Code: https://github.com/hazy/dpart