返回全部资讯
OpenAI 官方博客T1·基座大模型

OpenAI 提出指令层级训练法防御提示注入

原标题:The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
68AI 研判分

针对大模型易受提示注入和越狱攻击的安全痛点,研究提出“指令层级”概念。通过训练模型识别并优先执行特权指令(如系统提示),有效抵御恶意覆盖原始指令的攻击,提升模型鲁棒性。

报道正文

Today's LLMs are susceptible to prompt injections, jailbreaks, and other attacks that allow adversaries to overwrite a model's original instructions with their own malicious prompts.