研究者指出 ML 安全研究与安全实践之间存在缺口
AI 导读
据 X 用户 @wunderwuzzi23 表示，其六年前开始撰写 ML 攻击相关内容，主要原因是注意到 ML 安全研究与安全实践之间存在缺口。该用户提出，假设系统已被攻破是一种好策略，并建议追问：我们如何知道它发生了？我们打算怎么应对？
正文
When I started writing about ml attacks 6 years ago, the main reason was the gap I noticed between ml safety research and security.
It's a good strategy to assume stuff is compromised and ask question like:
- How would we even know it happened?
- What are we gonna do about it?