paperAugust 2026Unreviewed

Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitution

Ziliang Zhang, Yubo Zhu, Wei Tong, Jingyu Hua, Zijian Wang, Yuan Zhang, Sheng Zhong

Abstract

Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm for combining large language models (LLMs) with external knowledge sources. However, RAG systems remain vulnerable to prompt injection attacks, which may mislead the retriever or generator to expose sensitive database contents. To address this issue, we propose KFS-RAG, a defense that mitigates information leakage by reformulating the retrieved context. Specifically, our method first identifies a small set of influential key

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0051LLM Prompt Injection

Suggested from the entry's categories.

Cite

@misc{zhang2026mitigating,
  title = {{Mitigating Database Leakage in RAG Systems with Keyword-Grounded Fact Substitution}},
  author = {Ziliang Zhang and Yubo Zhu and Wei Tong and Jingyu Hua and Zijian Wang and Yuan Zhang and Sheng Zhong},
  year = {2026},
  month = aug,
  eprint = {2608.21656},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/f9b432133fc98cafe0353fb62319bdf7614e203d}
}