Ars Technica：Google 找到给 AI 设计蛋白质加水印的办法——生物设计工具"功效与威胁同源"的老问题有了对策
Google figures out how to watermark AI-designed proteins
评分 49
导读
Ars Technica：AI 造成的安全威胁几乎天天上新，但生物安全(biosecurity)这条线我们此前跑得相对靠前——能消化塑料、阻断毒蛋白的 AI 设计酶证明了工具威力，同一套蛋白质设计工具也能造毒素、改病毒蛋白行为；而识别威胁 DNA 序列的软件认不出 AI 设计的蛋白质(没人刻画到能判定)。该风险被提出近一年后仍无人知道能做什么，Google 现在给出了给 AI 设计的蛋白质加水印的方案。
主体与标签
Google#论文/研究#安全/对齐#Google
正文
AI-based tools seem to be causing security threats on a nearly daily basis, in part because we've been slow to recognize potential threats. One area where we seem to be ahead of the game, however, is in biosecurity.
As with most things biological, utility goes hand in hand with threats. We've developed increasingly sophisticated tools for designing proteins and seen some major successes, such as AI-designed enzymes that can digest plastics or block venom proteins . But these same tools could be used to make toxins or alter the behavior of viral proteins.
And the software we use to identify DNA sequences that encode potentially threatening proteins doesn't pick out AI-designed proteins , since nobody has characterized them well enough to know that they're threats. Nearly a year after that risk was flagged, it still wasn't clear what anyone could do about it.