ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning

Xiangyu Yin, Yi Qi, Chih-Hong Cheng

Abstract

Retrieval-Augmented Generation (RAG) improves the reliability of large language model applications by grounding generation in retrieved evidence, but it also introduces a new attack surface: corpus poisoning. In this setting, an adversary injects or edits passages so that they are ranked into the Top-$K$ results for target queries and then affect downstream generation. Existing defences against corpus poisoning often rely on content filtering, auxiliary models, or generator-side reasoning, which

Categories

Cite This Resource

@article{llmsec202600161,
  title = {ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning},
  author = {Xiangyu Yin and Yi Qi and Chih-Hong Cheng},
  year = {2026},
  url = {https://arxiv.org/abs/2603.22934},
}