Robust Context-Aware Detection of Malicious Instructions in Text

Abstract

The remarkable instruction-following ability of modern LLMs has enabled their practical use as the minds of agents that can autonomously complete increasingly complex tasks. Therein, however, also lies their vulnerability to attacks which embed malicious instructions in text, common variants of which are known as indirect prompt injection (IPI). A fundamental task in addressing this vulnerability is successful segmentation of a given text into benign and malicious sentences (if any). While a num

Categories

Framework mappings

Suggested from the entry's categories.

@misc{liu2026robust,
  title = {{Robust Context-Aware Detection of Malicious Instructions in Text}},
  author = {Buzhao Liu and Xinhang Ma and Yevgeniy Vorobeychik},
  year = {2026},
  month = aug,
  eprint = {2608.05430},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.05430}
}