1
RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems
动态评估智能体AI系统安全性的创新基准RIFT-Bench，通过自动化攻击测试揭示大模型潜在风险。
arXiv:2606.23927v1 Announce Type: new Abstract: Agentic AI systems powered by large language models (LLMs) are rapidly evolving into autonomous decisi…