PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models

Wei Zou, Runpeng Geng, Binghui Wang, Jinyuan Jia

Abstract

Demonstrates knowledge poisoning attacks against RAG systems where adversaries inject malicious texts into the knowledge database to manipulate LLM outputs.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400003,
  title = {PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models},
  author = {Wei Zou and Runpeng Geng and Binghui Wang and Jinyuan Jia},
  year = {2024},
  journal = {arXiv preprint},
  url = {https://arxiv.org/abs/2402.07867},
}