Leak It: A Probabilistic Approach to Training-Data Extraction from Black-Box Language Models

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 through a probabilistic lens, treating N samples from p(.|x) as an estimate of the output distribution and casting leakage signals as functionals of it. We extend the blind-baseline critique into the sampling regime: on WikiMIA a blind bag-of-words classifier reaches AUC 0.97 (TPR 0.90 at 5% FPR) and sampling adds nothing, while on an IID Pile split (MIMIR) neither self-concentration nor gold-continuation recovery significantly beats a blind baseline (incremental AUC 95% CI includes zero). Aggregate metrics hide the real harm. The same sampling verbatim-extracts training data for a tail of documents no blind attack can reach. On Pythia-6.9B, 83 of 500 Pile documents bearing a real identifier (16.6%; 21.3% of those bearing an email address) have that exact identifier reproduced AND not reproduced under a mismatched-prefix control, so each leak is attributable to that document, not to a globally common string. This per-document disclosure is invisible to aggregate AUC and grows with capacity (5.6% to 16.6% from 410M to 6.9B). The risk is uneven: identifier leakage is ~3x stronger in code than prose, though prose stays clearly positive and also grows with capacity (4.0% to 12.1%), while recovery of arbitrary held-out continuations is confined to code (+0.44 member gap on GitHub vs at most +0.014 on prose). Temperature and nucleus sampling matter little, a 16-token prefix suffices, and we detect no reduction from corpus deduplication. Privacy audits should report per-document extraction, decomposed by domain, not a single AUC. We release leakit, a black-box extraction-audit tool.

13 pages, 7 figures. Code: this https URL

Machine Learning (cs.LG); Computation and Language (cs.CL); Cryptography and Security (cs.CR)

arXiv:2608.00144 [cs.LG]

(or arXiv:2608.00144v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2608.00144 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.