AI RESEARCH
E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems
arXiv CS.AI
•
ArXi:2605.00955v1 Announce Type: cross Retrieval-Augmented Generation (RAG) equips large language models (LLMs) with external evidence by retrieving documents at inference time, but it also turns the retrieval corpusinto a sensitive asset. Under a black-box setting, an adversary given a candidate document can infer whether it has been ingested into the RAG knowledge base (i.e., document-level membership inference) solely from query response interactions, thereby leaking corpus coverage and the existence of sensitive topics.