Probabilistic 'Leak It' Shows Black‑Box LLMs Leak Identifiers Even Without Model Access
The paper introduces a sampling‑based, probabilistic framework that extracts exact training‑data identifiers from closed‑source LLMs. It demonstrates that even a simple blind bag‑of‑words baseline attains near‑perfect AUC, and that targeted extraction reveals up to 16% of documents leaking personal info, a risk hidden from aggregate metrics. The authors release an open‑source audit tool, leakit.