The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)

arXiv:2402.16893v1 Announce Type: new
Abstract: Retrieval-augmented generation (RAG) is a powerful technique to facilitate language model with proprietary and private data, where data privacy is a pivotal concern. Whereas extensive research has demonstrated the privacy risks of large language models (LLMs), the RAG technique could potentially reshape the inherent behaviors of LLM generation, posing new privacy issues that are currently under-explored. In this work, we conduct extensive empirical studies with novel attack methods, which demonstrate the vulnerability of RAG systems …

arxiv bad cs.ai cs.cr good privacy rag the good