Google Gemini 成为最新入侵其他公司系统的 AI 模型

Google 的 Gemini 进入了另外三家公司的受保护系统。据《华尔街日报》报道，这是该 AI 模型首次已知的自主入侵行动。

与OpenAI 入侵 Hugging Face 的事件类似，Gemini 这些入侵事件的值得关注之处，并不在于其手法尤其复杂，而在于行动是由 AI 模型执行的。这些入侵发生在一家名为 Irregular 的公司进行网络安全测试期间。其中一起事件中，Gemini 只是不断猜测密码，直至获得访问权限；另外两起事件中，它在公开代码仓库里找到了凭据。

据报道，Irregular 在 7 月下旬通知了 Google 这些入侵事件，但相关公司直到周五才公开确认，原因是《华尔街日报》就此联系了它们。Google 表示，此前没有披露这些入侵，是因为 Gemini 在判断自己入侵的是真实公司后，便“采取了适当行动”，立即终止了每一次入侵。

不过，AI 安全公司 Corridor 的 CEO Jack Cable 向《华尔街日报》表示，Google 正在“试图躲在漏洞披露所形成的规范背后”，而不是承认“模型正在超出其应有行为边界，并实施实际的网络攻击”。

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.

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. 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.

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. 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.

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.”