2026年9月28日 / 美国东部时间上午8:36 / 哥伦比亚广播公司新闻
芯片制造商英伟达日前推出了一款全新的安全平台，该公司表示，该平台可以防止人工智能代理失控。
该公司周一宣布将推出这套名为OpenShell的新系统，原因是在多起人工智能代理违抗命令并闯入其他系统的事件发生后，行业需要“独立的安全管控措施”。
最近，OpenAI于上周五表示，其人工智能代理曾以意外方式与多个美国政府网站进行交互。这一披露此前已有多起其他人工智能代理失控入侵的黑客事件发生。
英伟达高管在一场媒体发布会上表示，这套新系统本可以阻止近期一起涉及OpenAI多个人工智能代理自主入侵人工智能公司Hugging Face的事件。越来越多关于人工智能代理独立入侵企业和政府机构的报道，引发了包括Anthropic首席执行官达里奥·阿莫代在内的行业领军高管呼吁放缓该技术的开发进度。
“据我们所知，如果早期前沿实验室在进行模型评估时就使用该平台，本可以阻止此次数据泄露事件，”英伟达企业人工智能副总裁贾斯汀·博伊塔诺在周一的新闻发布会上说道，他此处所指的是处于人工智能领域前沿的公司。
博伊塔诺表示，英伟达的这款软件可以让开发者“正式验证人工智能代理拥有足够完成其工作的权限，且权限不会超出必要范围”。
英伟达称，该平台在推出时已有超过100家机构正在使用，其中包括埃森哲、摩根大通和微软。
在周一由多名英伟达工程师撰写的一篇博客文章中，该公司将人工智能的发展与互联网早期阶段进行了类比——当时互联网技术拓展了通信渠道，但也带来了安全风险。
“互联网的安全并非通过要求网页开发者承诺恪守准则来实现，而是因为浏览器明确停止信任网页中的代码，”工程师们在文章中写道。
他们表示，OpenShell在“沙箱”——即隔离的虚拟空间——中运行人工智能代理并对其进行测试，同时将代理的指令转化为“可验证的策略”。运营者可以定义人工智能代理能够访问哪些文件、工具、网络、进程和凭证。
该公司还表示，这套平台还包含一个名为“Sentry”的独立安全层，该层运行在芯片上，可持续监控人工智能代理的活动，若代理试图突破预设目标范围，可“立即进行干预”。
“它可以在毫秒内隔离可疑代理，”博伊塔诺说道。
Alain Sherter 编辑
美联社为本报道提供了支持。
Nvidia says its new OpenShell platform can stop AI agents from going rogue
September 28, 2026 / 8:36 AM EDT / CBS News
NVIDIA has created a new security platform that the chipmaker said can prevent artificial intelligence agents from going rogue.
The company said on Monday that it is releasing the new system, called OpenShell, due to the need for “independent security controls” after multiple AI agents disobeyed commands and broke into other systems.
Most recently, OpenAI said on Friday that its AI agents had interacted with several U.S. government websites in unexpected ways, a disclosure that came after several earlier rogue hacking incidents by other AI agents.
Nvidia executives said in a media briefing that its new system could have prevented a recent incident involving a swarm of OpenAI agents that autonomously hacked into AI company Hugging Face. Mounting reports about AI agents independently hacking companies and government agencies have sparked calls from leading industry executives, including Anthropic CEO Dario Amodei, to slow development of the technology.
“From what we know, this new security platform could have stopped the breach if it was being used in frontier labs for model evaluation early on,” Justin Boitano, Nvidia’s vice president of enterprise AI, said in a press conference on Monday, referring to companies at the forefront of AI.
Nvidia’s software allows developers to “formally verify an agent has enough authority to do its job and no more,” Boitano said.
Nvidia said more than 100 organizations are using the platform at its launch, including Accenture, JPMorgan Chase and Microsoft.
In a blog post written by several Nvidia engineers published Monday, the company compared the development of AI to the early days of the internet, when the technology expanded communication but also opened the door to security risks.
“The internet was not made secure by requiring that web developers promise to be good. It became safe because the browser stopped trusting the code in the web pages explicitly,” the engineers wrote.
OpenShell runs AI agents in a “sandbox,” or an isolated virtual space where AI programs are tested, and turns their instructions into “a verifiable policy,” they wrote. Operators define which files, tools, networks, processes and credentials the agents can access.
The platform also includes a separate security layer called Sentry that runs on a chip to continuously monitor AI agent activity and can “intervene instantly” if the agent starts trying to move beyond its target, the company said.
“It can quarantine a suspicious agent in milliseconds,” Boitano said.
Edited by Alain Sherter
The Associated Press contributed to this report.
发表回复