2 papers
cs.CR2026
IH-Benchmark: A Conflict-Centered Benchmark for Instruction-Hierarchy Robustness in LLM Applications
Conor McCauley, Zeliang Kan, Jason Martin
When a language model receives conflicting instructions from different priority levels, which one does it actually follow? This question lies at the heart of reliable LLM deploymen…
cs.CR2025
LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge
Sahar Abdelnabi, Aideen Fay, Ahmed Salem +22
Indirect prompt injection attacks exploit a fundamental weakness of LLMs: executing unauthorized tasks from untrusted sources. Despite the practical significance of this attack vec…