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.

A Review of the Role of Causality in Developing Trustworthy AI Systems

“…It is further argued that the models learned through causal features generalize better to distribution shifts and provide better privacy guarantees than equivalent association models. This has resulted in a growing body of work exploring causal models against privacy attacks [42,60,72,92,114,261]. We segregate these methods into pre-, in-and post-processing methods (refer to figure 6).…”