Black-Box Membership Inference via Word-Level Probability Estimation

Abstract

Membership inference attacks (MIAs) have emerged as critical tools for auditing privacy risks in large language models (LLMs), aiming to determine whether a given text was included in a model's training corpus. However, most existing MIAs require access to per-token logits or probabilities, making them inapplicable in practice to proprietary LLMs that expose only textual continuations. To address this underexplored setting, we propose Word-level Probability MIA (WPMIA), a statistically principle

Categories

Framework mappings

Suggested from the entry's categories.

@misc{niu2026blackbox,
  title = {{Black-Box Membership Inference via Word-Level Probability Estimation}},
  author = {Shengjie Niu and Yeheng Ge and Jian Huang},
  year = {2026},
  month = sep,
  eprint = {2609.10611},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.10611}
}