PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems

Haozhen Wang, Haoyue Liu, Jionghao Zhu, Zhichao Wang, Yongxin Guo, Xiaoying Tang

Abstract

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is often hindered by issues such as outdated knowledge and the tendency to generate hallucinations. To address these limitations, Retrieval-Augmented Generation (RAG) systems have been introduced, enhancing LLMs with external, up-to-date knowledge sources. Despite their advantages, RAG systems remain vulnerable to adversarial attacks, with data poisoning

Categories

Cite This Resource

@article{llmsec202600159,
  title = {PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems},
  author = {Haozhen Wang and Haoyue Liu and Jionghao Zhu and Zhichao Wang and Yongxin Guo and Xiaoying Tang},
  year = {2026},
  url = {https://arxiv.org/abs/2603.25164},
}