On Reliability of Membership Inference Vulnerability Evaluation

Excerpt

arXiv:2605.25819v2 Announce Type: replace Abstract: Membership inference attacks (MIAs) are popular methods for empirically assessing the leakage of sensitive information in the training data through models or statistics learned from the data. The MI vulnerability is often evaluated through a binary classifier that tries to predict whether a particular sample was in the training data. In order to evaluate the effectiveness of MIAs multiple \textit{shadow models} are trained using random partitio