Quantifying Membership Disclosure Risk for Tabular Synthetic Data Using Kernel Density Estimators

ArXi:2603.10937v1 Announce Type: new The use of synthetic data has become increasingly popular as a privacy-preserving alternative to sharing real datasets, especially in sensitive domains such as healthcare, finance, and graphy. However, the privacy assurances of synthetic data are not absolute, and remain susceptible to membership inference attacks (MIAs), where adversaries aim to determine whether a specific individual was present in the dataset used to train the generator.