LongPIBench: A Long-Context Benchmark for Prompt Injection

Abstract

Prompt injection attacks pose a serious security risk to large language models in real-world applications. However, existing prompt injection benchmarks primarily focus on short-context inputs, leaving the attacks and defenses in long-context settings largely unexplored. This gap leads to a substantial overestimation of the effectiveness of current defenses. In this paper, we bridge the gap by introducing LongPIBench, a long-context benchmark for prompt injection covering 4 realistic application

Categories

Framework mappings

Suggested from the entry's categories.

@misc{liu2026longpibench,
  title = {{LongPIBench: A Long-Context Benchmark for Prompt Injection}},
  author = {Yupei Liu and Yuqi Jia and Neil Zhenqiang Gong and Jinyuan Jia},
  year = {2026},
  month = aug,
  eprint = {2608.28411},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.28411}
}