Membership Inference Attacks on Tokenizers of Large Language Models

ArXi:2510.05699v3 Announce Type: replace-cross Membership inference attacks (MIAs) are widely used to assess the privacy risks associated with machine learning models. However, when these attacks are applied to pre-trained large language models (LLMs), they encounter significant challenges, including mislabeled samples, distribution shifts, and discrepancies in model size between experimental and real-world settings. To address these limitations, we