Ask HN: 我们准备好迎接漏洞成为文字而非代码的时代了吗?
2 分•作者: lielcohen•4 天前
到目前为止,安全领域一直仰仗数学。缓冲区溢出、SQL注入、密码学缺陷——这些都是确定性的、可测试的、可以形式化验证的。
但现在,我们正在向智能体授予终端访问权限和API密钥。攻击载体正在变成自然语言。一个智能体会被提示词“社会工程”;另一个则会产生虚假数据并将其传递下去。
试图保护这些系统,感觉就像试图编写一个能够捕捉所有可能谎言的正则表达式。我们已经将安全的基础从数字转移到了文字,而且我认为我们还没有弄清楚这意味着什么。
有人在思考针对此问题的实际架构解决方案吗?不仅仅是“使用另一个LLM来保护LLM”——这感觉像是循环论证。需要一些根本不同的东西。
(非英语母语者,使用AI润色了语法。)
查看原文
Until now, security has been math. Buffer overflows, SQL injections, crypto flaws — deterministic, testable, formally verifiable.<p>But we're giving agents terminal access and API keys now. The attack vector is becoming natural language. An agent gets "socially engineered" by a prompt; another hallucinates fake data and passes it down the chain.<p>Trying to secure these systems feels like trying to write a regex that catches every possible lie. We've shifted the foundation of security from numbers to words, and I don't think we've figured out what that means yet.<p>Is anyone thinking about actual architectural solutions to this? Not just "use another LLM to guard the LLM" — that feels like circular logic. Something fundamentally different.<p>(Not a native English speaker, used AI to clean up the grammar.)