arXiv cs.LG
· Papers
Leak It: A Probabilistic Approach to Training-Data Extraction from Black-Box Language Models
arXiv:2608.00144v1 Announce Type: new Abstract: Membership inference (MIA) on language models is usually summarised by an aggregate ROC-AUC, but such evaluations are confounded: model-free blind baselines separate members from non-members from surface text alone. We study black-box, sampling-based training-data leakage