Prompt Injection Attack Against LLM-Integrated Applications

Yi Liu, Gelei Deng, Yuekang Li, Kailong Wang, Tianwei Zhang, Yepang Liu, Haoyu Wang, Yan Zheng, Yang Liu

Abstract

First comprehensive survey of prompt injection attacks against LLM-integrated applications, categorizing attacks and defenses with a unified framework.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400025,
  title = {Prompt Injection Attack Against LLM-Integrated Applications},
  author = {Yi Liu and Gelei Deng and Yuekang Li and Kailong Wang and Tianwei Zhang and Yepang Liu and Haoyu Wang and Yan Zheng and Yang Liu},
  year = {2024},
  journal = {ACM Computing Surveys},
  url = {https://arxiv.org/abs/2306.05499},
}