CleanBase: Detecting Malicious Documents in RAG Knowledge Databases

Abstract

Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully crafted injected prompts into the knowledge database. When a user issues a question targeted by the attack, the RAG system may retrieve these malicious documents, whose injected prompts mislead it into generating attacker-specified answers, thereby compromising the integrity of the RAG system. In this work, we propose CleanBase, a method to detect

Categories

Framework mappings

Suggested from the entry's categories.

@misc{jin2026cleanbase,
  title = {{CleanBase: Detecting Malicious Documents in RAG Knowledge Databases}},
  author = {Weifei Jin and Xilong Wang and Wei Zou and Jinyuan Jia and Neil Gong},
  year = {2026},
  month = may,
  eprint = {2605.00460},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.00460}
}