SOURCE-LINKED INTELLIGENCE

LongPIBench: A Long-Context Benchmark for Prompt Injection

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

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 scenarios: paper peer review, resume screening, code review, and email summary. For each scenario,

Read original source ↗ Open in workspace

recordType

paper

region

Global