arXiv:2606. 17464v1 Announce Type: new Abstract: Membership inference attacks (MIAs) are a canonical way to assess a machine learning model's privacy properties.
By Jeffrey G. Wang, Jason Wang, Marvin Li, Seth Neel
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.
By Victor Maricato
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.
By Victor Maricato
Large Language Models (LLMs) raise growing concerns about privacy leakage and copyright compliance. Membership inference is a key tool for assessing such risks, but existing studies mainly focus on whether specific samples or sample-based data units are used for training.
The study re‑runs the OLMo 2 1B language model with controlled training exposure, swapping selected training chunks with matched documents to assess membership inference. Using a counterfactual run from the same seed, the authors find that a single exposure modestly increases a document’s likelihood but rarely allows reliable identification; the reference‑ratio method achieves an AUC of 0.767 and detects 3.8 % of members at a 1 % false‑positive rate. Even with matched references, document‑level variability limits individual inference, and the authors plan to release checkpoints, log‑probabilities, and evaluation data.
By Ali Banaei, Muhammad Shahab Shahzad, Gerald Q. Maguire Jr., Marco Chiesa, Dejan Kosti\'c
arXiv:2606. 24408v1 Announce Type: new Abstract: Assessing the privacy of large language models (LLMs) presents significant challenges.
By Lorenzo Rossi, Bart{\l}omiej Marek, Franziska Boenisch, Adam Dziedzic