行业动态
x.com ·
@GaryMarcus
研究：AI生成补丁成功率仅26%，且易引入新漏洞
1Password研究测试6000多个AI生成补丁，发现仅26%能修复漏洞，4.5%引入新漏洞，且人工审查成本高于自行修复。作者Gary Marcus评论称，AI补丁可能带来重大安全风险。
AI推荐理由 引用1Password研究，指出AI生成补丁成功率低且可能引入新漏洞，对AI在安全领域的应用有警示作用，数据具体，来源可信。
80
浏览 29,458
点赞 510
评论 23
转发 78
正文
“完全由LLM生成、未经人工审查的补丁的期望值是净负面的，而且差距相当大。”
Hedgie@HedgieMarkets
🦔AI只能修复26%的安全漏洞。1Password的研究人员使用Claude和ChatGPT针对真实漏洞运行了超过6000个AI生成的补丁。有一半的时间，AI未能修复原始漏洞。4.5%的时间，它创造了一个以前不存在的新漏洞。研究人员还发现，检查AI生成的安全补丁比你自己编写修复程序更费力。
他们的结论很直白。“完全由LLM生成、未经人工审查的补丁的期望值是净负面的，而且差距相当大。”
我的看法
OpenAI今年夏天启动了一个名为“修补地球”的项目，让AI发现漏洞并生成修复程序。这些研究人员针对其中一个相同的漏洞运行了270个补丁。零个干净的修复。一个都没有。每个修复了原始问题的补丁都在这个过程中创造了新的漏洞。通过OpenAI项目提交修复的合作伙伴产生了研究人员归类为最糟糕的结果：它没有完全修复漏洞，而且还引入了一个新的漏洞。
如果你不是以写代码为生，这对你意味着什么。公司正在使用这些AI工具来修补运行你的银行、医院、手机的软件。宣传一直是“AI比人类更快地发现和修复安全漏洞。”这项研究表明，AI修复程序出问题的可能性是正常工作的四倍，而且有三分之一的时间它会重蹈人类程序员已经犯过的错误。审查AI的工作比自己做要花更长的时间。所以，当你试图验证输出时，速度优势就消失了，而大多数公司不会这样做，因为整个目的就是为了更快。我认为我们将看到重大安全漏洞追溯到无人检查的AI生成补丁，而发布这些补丁的公司会责怪工具，而不是责怪信任它的决定。
Hedgie🤗
研究[1password.com/files/resource…](https://1password.com/files/resources/frontier-models-vulnerability-patches-flawed.pdf)SX
[🔗 查看引用的推文](https://x.com/HedgieMarkets/status/2096398823140503713)
查看原文（中文正文为 AI 翻译）
“The expected value of a fully LLM-generated, non-human-reviewed patch is a net-negative by a considerable margin.”
Hedgie@HedgieMarkets
🦔AI can only fix security vulnerabilities 26% of the time. Researchers at 1Password ran over 6,000 AI-generated patches using Claude and ChatGPT against real vulnerabilities. Half the time the AI failed to fix the original bug. 4.5% of the time it created a brand new vulnerability that didn't exist before. And the researchers found that checking an AI-generated security patch takes more effort than just writing the fix yourself.
Their conclusion was blunt. "The expected value of a fully LLM-generated, non-human-reviewed patch is a net-negative by a considerable margin."
My Take
OpenAI launched a program this summer called "Patch the Planet" where AI finds bugs and generates the fixes. These researchers ran 270 patches against one of those same bugs. Zero clean fixes. Not one. Every patch that fixed the original problem created a new vulnerability in the process. The partner that submitted a fix through OpenAI's program produced what the researchers classified as the worst possible outcome, it didn't fully fix the bug and it introduced a new exploit on top of it.
Here's what this means if you don't write code for a living. Companies are using these AI tools to patch the software that runs your bank, your hospital, your phone. The pitch has been "AI finds and fixes security holes faster than humans." This study says the AI fix is four times more likely to be broken than working, and a third of the time it recreates the exact same mistakes human programmers already made. Reviewing the AI's work takes longer than doing it yourself. So the speed advantage disappears the moment you try to verify the output, which most companies won't do because the entire point was to move faster. I think we're going to see major breaches traced back to AI-generated patches that nobody checked, and the companies that shipped them are going to blame the tool instead of the decision to trust it.
Hedgie🤗
Study[1password.com/files/resource…](https://1password.com/files/resources/frontier-models-vulnerability-patches-flawed.pdf)SX
[🔗 View Quoted Tweet](https://x.com/HedgieMarkets/status/2096398823140503713)