Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models

Jingwei Yi, Yueqi Xie, Bin Zhu, Keegan Hines, Emre Kiciman, Guangzhong Sun, Xing Xie, Fangzhao Wu

Abstract

Provides a benchmark for indirect prompt injection attacks and evaluates several defense strategies including perplexity-based detection and sandwich defense.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400047,
  title = {Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models},
  author = {Jingwei Yi and Yueqi Xie and Bin Zhu and Keegan Hines and Emre Kiciman and Guangzhong Sun and Xing Xie and Fangzhao Wu},
  year = {2024},
  journal = {arXiv preprint},
  url = {https://arxiv.org/abs/2312.14197},
}