High Epsilon Synthetic Data Vulnerabilities in MST and PrivBayes

Synthetic data generation (SDG) has become increasingly popular as a privacy-enhancing technology. It aims to maintain important statistical properties of its underlying training data, while excluding any personally identifiable information. There have been a whole host of SDG algorithms developed in recent years to improve and balance both of these aims. Many of these algorithms provide robust differential privacy guarantees.
However, we show here that if the differential privacy parameter $\varepsilon$ is set too high, then unambiguous privacy leakage can …

algorithms balance cs.cr data high host important information personally identifiable information popular privacy sdg synthetic synthetic data technology training training data vulnerabilities