技术博客/A small number of samples can poison LLMs of any size
Anthropic进阶2025-10-09· 10 分钟· RAG 与记忆
A small number of samples can poison LLMs of any size
Alignment Oct 9, 2025 Read the paper In a joint study with the UK AI Security Institute and the Alan Turing Institute, we found that as few as 250 mal
本文需解锁后阅读
免费开放 3 篇精选工程博客（列表置顶）。其余文章登录后可阅读全文。