📄️ 🟢 Introduction
Prompt hacking is a term used to describe a type of attack that exploits the vulnerabilities of %%LLMs|LLM%%, by manipulating their inputs or prompts. Unlike traditional hacking, which typically exploits software vulnerabilities, prompt hacking relies on carefully crafting prompts to deceive the LLM into performing unintended actions.
📄️ 🟢 提示注入
提示注入是一种用于劫持语言模型输出(@branch2022evaluating)(@crothers2022machine)(@goodside2022inject)(@simon2022inject)的技术。
📄️ 🟢 提示泄漏
提示泄漏是一种提示注入的形式，其中模型被要求输出自己的提示。
📄️ 🟢 越狱
越狱（Jailbreaking）是一种提示注入技术，用于绕过语言模型（LLM）的创建者放置在其上的安全和审查功能(@perez2022jailbreak)(@brundage_2022)(@wang2022jailbreak)。
🗃️ 🟢 Defensive Measures
9 个项目
🗃️ 🟢 Offensive Measures
8 个项目