Skip to content
Search
paperJune 2024ReviewedOpen access

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

ACM Computing Surveys

View resourcePDF

Abstract

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

Categories

Prompt InjectionSurveys
#survey#prompt-injection#taxonomy

Framework mappings

OWASP Top 10 for LLM Applications
  • LLM01Prompt Injection
MITRE ATLAS
  • AML.T0051LLM Prompt Injection

Cite

@article{liu2024prompt,
  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},
  month = jun,
  journal = {ACM Computing Surveys},
  eprint = {2306.05499},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2306.05499}
}