Google’s Gemini is the latest AI model to hack other companies

Google 的 Gemini 成为最新一个入侵其他公司的 AI 模型

Google’s Gemini accessed the protected systems of three other companies in what The Wall Street Journal reports were the AI model’s first autonomous hacks. 据《华尔街日报》报道，Google 的 Gemini 模型近日访问了三家公司的受保护系统，这是该 AI 模型首次实现自主入侵。

Similar to OpenAI’s breach of Hugging Face, the Gemini hacks were less noteworthy for being particularly sophisticated and more for the fact that they were conducted by an AI model. 与此前 OpenAI 入侵 Hugging Face 的事件类似，Gemini 的这些入侵行为之所以引人注目，并非因为其技术手段极其复杂，而是因为它们是由 AI 模型自主执行的。

These breaches took place during cybersecurity testing by a company called Irregular. In one case, Gemini simply guessed passwords until it gained access; in the other two, it found credentials in a public repository. 这些入侵行为发生在一项由名为 Irregular 的公司进行的网络安全测试期间。在其中一个案例中，Gemini 通过不断猜测密码直到成功获取访问权限；在另外两个案例中，它则是在公共代码库中发现了凭据。

Irregular reportedly notified Google about the hacks in late July, but the companies did not confirm them publicly until Friday, after the WSJ reached out. 据报道，Irregular 在 7 月下旬就已将这些入侵事件通知了 Google，但直到周五《华尔街日报》介入询问后，双方才公开确认了此事。

Google said it hadn’t previously revealed the hacks because Gemini had “acted appropriately” by ending each breach as soon as it determined it had hacked a real company. Google 表示，此前未披露这些入侵事件是因为 Gemini 在确定自己入侵的是一家真实公司后，立即停止了操作，表现得“非常得体”。

However, Jack Cable, the CEO of AI security company Corridor, told the WSJ that Google was “trying to hide behind the norms that have been created for vulnerability disclosure,” rather than acknowledging that “models are going outside the bounds of what they should be doing, and doing actual cyberattacks.” 然而，AI 安全公司 Corridor 的首席执行官 Jack Cable 对《华尔街日报》表示，Google 只是“试图躲在为漏洞披露所制定的规范背后”，而不是承认“模型正在越界，并执行了实际的网络攻击”。