arXiv Machine Learning By Victor Maricato

Leak It: Per-Document Extraction Beyond Aggregate Membership Inference

Read the original on arXiv Machine Learning →

arXiv:2608. 00144v2 Announce Type: replace Abstract: Membership inference (MIA) on language models is usually summarised by aggregate ROC-AUC, but such evaluations are confounded: model-free blind baselines can separate members from non-members using surface text alone.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.