NFCorpus

Five Queries Are Enough: Query-Efficient and Surrogate-Free Membership Inference Attacks on RAG via Entailment

arXiv:2605.24312v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) has become central to large language model (LLM) deployments, grounding responses in enterprise or proprietary data to reduce hallucinations. However, this design introduces a new privacy risk: model outputs may signal the presence of specific documents in the retrieval corpus, enabling membership inference attacks (MIAs) that leak sensitive information. Existing MIAs are feasible, but they often rely on...