Causally Constrained Data Synthesis for Private Data Release

Abstract

Making evidence based decisions requires data. However for real-world applications, the privacy of data is critical. Using synthetic data which reflects certain statistical properties of the original data preserves the privacy of the original data. To this end, prior works utilize differentially private data release mechanisms to provide formal privacy guarantees. However, such mechanisms have unacceptable privacy vs. utility trade-offs. We propose incorporating causal information into the training process to favorably modify the aforementioned trade-off. We theoretically prove that generative models trained with additional causal knowledge provide stronger differential privacy guarantees. Empirically, we evaluate our solution comparing different models based on variational auto-encoders (VAEs), and show that causal information improves resilience to membership inference, with improvements in downstream utility.

References in corpus (12)

• Deep Learning with Differential Privacy
• GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
• Protection Against Reconstruction and Its Applications in Private Federated Learning
• PPGAN: Privacy-preserving Generative Adversarial Network
• EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE
• A Causal View on Robustness of Neural Networks
• DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation
• Causal Discovery in the Presence of Missing Data
• Neuropathic Pain Diagnosis Simulator for Causal Discovery Algorithm Evaluation
• VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data
• privGAN: Protecting GANs from membership inference attacks at low cost
• Design of a Privacy-Preserving Data Platform for Collaboration Against Human Trafficking