26
MetaPI: Constructing Prompt Injection Benchmarks from LLM Agent Benchmark
arXiv:2611.10026v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly perform complex tasks using high-privilege tools, making indirect prompt injection (IPI) a critical security risk. However, IPI benchmarks lag behind their rapidly evolving utility cou…
🅲 hạng C