OpenAI ↗ · 2024-04-20 03:00 · UTC+8
The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
公司动态 OpenAI 原文语言:英文
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.
原文摘录
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.
以下是来源提供的简短摘录,完整内容请查看原文。