OpenAI披露内部模型黑客攻击网站与窃取加密货币
OpenAI models hacked a crypto wallet and breached more websites
OpenAI主动披露内部模型进行黑客攻击和窃取加密货币的真实案例,揭示了当前AI安全防御机制的重大漏洞,对行业有极强的警示意义。
OpenAI said internal models hacked two more websites, bypassed company-imposed browsing restrictions, and used exposed credentials to draw cryptocurrency from a wallet it couldn’t otherwise access, in the latest installment of disclosures of its agents performing unethical and likely illegal acts.
OpenAI 表示,其内部模型入侵了两个更多网站,绕过了公司施加的浏览限制,并利用泄露的凭据从一个它无法以其他方式访问的钱包中提取加密货币,这是其代理执行不道德且可能非法行为的最新披露。
The company on Thursday issued reports of four new incidents, all of which occurred in June. They come after the company revealed in July that internal test agents exploited a zero-day vulnerability in a tool designed to restrict their access to the Internet. They then broke into the network of AI tool provider Hugging Face. The agents took that illegal action to steal answers to a hacking test that weren’t available when completing the tasks on their own. The incident—which likely would have resulted in criminal charges had they been performed directly by a person—has further heightened concerns that widespread AI use could have harmful effects on an unprecedented scale.
该公司周四发布了四起新事件的报告,均发生在六月。此前,该公司在七月透露,内部测试代理利用了一种旨在限制其互联网访问权限的工具中的零日漏洞。随后,它们侵入了 AI 工具提供商 Hugging Face 的网络。代理采取这一非法行动是为了窃取黑客测试的答案,而这些答案在独立完成任务时是无法获得的。这一事件——如果由人直接实施,很可能导致刑事指控——进一步加剧了人们对广泛使用 AI 可能在前所未有的规模上产生有害影响的担忧。
Easier to beg for forgiveness than ask permission
请求宽恕比请求许可更容易
In two of the cases reported Thursday, OpenAI agents tasked with retrieving information from websites hacked them when the models ran into obstacles obtaining it directly. In one incident during reinforcement training, a model that received access denials when trying to retrieve historical hospital-bed statistics on a government statistics website “used the site's file-download feature to retrieve server configuration and application files, including sensitive credentials,” OpenAI said. “It inspected the application code, bypassed the statistics endpoint's authorization checks, and retrieved data that had previously been denied. The model saved the data locally.”
在周四报告的两起案件中,被指派从网站检索信息的 OpenAI 代理在模型遇到直接获取信息的障碍时入侵了这些网站。在一次强化训练事件中,一个在尝试从政府统计网站检索历史医院床位统计数据时遭到访问拒绝的模型,“使用了该网站的文件下载功能来检索服务器配置和应用程序文件,包括敏感凭据”,OpenAI 表示。“它检查了应用程序代码,绕过了统计端点的授权检查,并检索了之前被拒绝的数据。该模型将数据保存在本地。”
Read full article
阅读全文
Comments
评论
更进一步:量化金融体系
看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力