1
PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections
论文提出PI-Hunter，自动发现并精准定位大模型提示注入漏洞，为AI安全红队测试提供新方案。
arXiv:2606.12737v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external t…