Differentially Private Synthetic Data Generation via Lipschitz-Regularised Variational Autoencoders

Understand

Synthetic data has been hailed as the silver bullet for privacy preserving data analysis.

• If a record is not real, then how could it violate a person's privacy? In addition, deep-learning based generative models are employed successfully to approximate complex high-dimensional distributions from data and draw realistic samples from this learned distribution.
• It is often overlooked though that generative models are prone to memorising many details of individual training records and often generate synthetic data that too closely resembles the underlying sensitive training data, hence violating strong privacy regulations as, e.g., encountered in health care.
• Differential privacy is the well-known state-of-the-art framework for guaranteeing protection of sensitive individuals' data, allowing aggregate statistics and even machine learning models to be released publicly without compromising privacy.