A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data

arXiv:2301.10053v3 Announce Type: replace-cross
Abstract: Recent advances in synthetic data generation (SDG) have been hailed as a solution to the difficult problem of sharing sensitive data while protecting privacy. SDG aims to learn statistical properties of real data in order to generate "artificial" data that are structurally and statistically similar to sensitive data. However, prior research suggests that inference attacks on synthetic data can undermine privacy, but only for specific outlier records. In this work, we introduce a new attribute …

artificial arxiv attacks cs.cr cs.lg data learn linear order privacy problem protecting real sdg sensitive sensitive data sharing solution synthetic synthetic data