大模型对齐与安全

Enhancing Reliability in LLM-Integrated Robotic Systems: A Unified Approach to Security and Safety

Wenxiao Zhang, Xiangrui Kong, Conan Dewitt, Thomas Bräunl, Jin B. Hong

机构 * The University of Western Australia（西澳大学） 纠错

专题命中 提示注入 ：safety(title,abstract)；prompt injection(abstract)；分类 cs.AI

A Whole New World: Creating a Parallel-Poisoned Web Only AI-Agents Can See

Shaked Zychlinski

机构 * JFrog 纠错

专题命中 提示注入 ：prompt injection(abstract)；分类 cs.AI、cs.CY

Comments 10 pages, 1 figure