⚡Megatron LLM Hub
←返回搜索
Twitter

Check Point 披露在越狱包中注入广告的「提示广告软件」Haiou

提示层注入可绕过模型约束,自托管 LLM 与 Agent 面临同类注入面。
llmai_agent供应链报告
When an AI jailbreak starts injecting ads: meet #Haiou, an example of Prompt Adware. A glimpse into a new class of unwanted software. Read more 👇 https://t.co/Gje90C8cYR