홈 › Papers

CAPTURE: Context-Aware Prompt Injection Testing and Robustness Enhancement

Prompt injection remains a major security risk for large language models. However, the efficacy of existing guardrail models in context-aware settings remains underexplored, as they often rely on static attack benchmarks. Additionally, they have over-defense tendencies. We introduce CAPTURE, a novel context-aware benchmark assessing both attack detection and over-defense tendencies with minimal in-domain examples. Our experiments reveal that current prompt injection guardrail models suffer from high false negatives in adversarial cases and excessive false positives in benign scenarios, highlighting critical limitations.

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반