Author name: Maosen Zhang, Jianshuo Dong, Boting Lu, Wenyue Li, Xiaoping Zhang, Tianwei Zhang, Han Qiu

arXiv:2605.05818v1 Announce Type: cross
Abstract: Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to leverage external knowledge, but also exposes valuable RAG databases to leakage attacks. As RAG systems grow more complex an…