从数周到数小时：SentinelOne 如何用 OpenAI 加速恶意软件逆向研究

“How much of the world of malware can I actually map?”

恶意软件的世界，我究竟能摸清多少？

“At the moment, we're only able to reverse very small numbers of pieces of software.”

目前我们只能逆向分析极少数软件。

“Something that would've taken a top flight researcher four weeks, six weeks to do, now it's doing at human-level output in something like eight hours.”

顶级研究员原本要花四到六周的工作，现在大约八小时就能达到人类水平的输出。

“Well, this is a relationship now between these two pieces of previously unrelated, uh, malware.”

这两个原本毫不相干的恶意软件之间，现在有了关联。

“That's a kind of intelligence that we were never able to afford before.”

这种情报以前我们根本负担不起。

“But OpenAI is shifting the advantage to defenders by providing expert level cyber capability to everyone in the development team.”

而 OpenAI 正把专家级网络安全能力交给开发团队的每一个人，把优势转向防御方。