OpenAI News·· 2024-04-20AI 评分33
OpenAI 提出指令层级训练 LLM 优先处理特权指令
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
AI 导读
OpenAI 提出“指令层级”方法，旨在训练大语言模型（LLM）优先处理特权指令。当前 LLM 易受提示注入和越狱攻击，导致原始指令被恶意覆盖。该研究通过调整指令优先级来增强模型安全性。
原文
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.
来源：OpenAI News · openai.com