On the Utility Recovery Incapability of Neural Net-based Differential Private Tabular Training Data Synthesizer under Privacy Deregulation

Liu, Yucong, Wang, Chi-Hua, Cheng, Guang

arXiv.org Artificial Intelligence 

Devising procedures for auditing generative model privacy-utility tradeoff is an important yet unresolved problem in practice. Existing works concentrates on investigating the privacy constraint side effect in terms of utility degradation of the train on synthetic, test on real paradigm of synthetic data training. We push such understanding on privacy-utility tradeoff to next level by observing the privacy deregulation side effect on synthetic training data utility. Surprisingly, we discover the Utility Recovery Incapability of DP-CTGAN and PATE-CTGAN under privacy deregulation, raising concerns on their practical applications. The main message is Privacy Deregulation does NOT always imply Utility Recovery.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found