arXiv stat.ML
· Papers
Membership Inference Attacks for Unseen Classes
arXiv:2506.06488v3 Announce Type: replace-cross Abstract: A key tool in developing safe AI models is emph{data auditing}, i.e., using statistical tools to determine whether harmful content may have been used in the training data of a black-box model. Unfortunately, most emph{membership inference attacks} (MIAs) used