11-20 更新 实时
首页/ AI 大模型/ 正文

Google 打造镜像维度网络测试 Chrome 智能体

AI 大模型 来源:Wired 2026-11-20 01:00 0 阅读 机器翻译
Google 打造镜像维度网络测试 Chrome 智能体

Google 在今天的博客文章中首次详细介绍的“Mirror Dimension”(镜像维度),是一个规模庞大、类型多样却完全隔离的网络生态,由 Chrome 团队全权掌控。它包含大量网站和平台——包括社交媒体网站、购物网站和银行仪表盘——这些站点都具备真实网站的全部组件与属性。浏览助手智能体必须在 Chrome 中与这些站点交互并完成任务,方式与它们在真实互联网上完全一样。而且在过程中它们还会不断面临韧性测试,例如隐藏的提示注入攻击,以检验自身的防御能力。

“智能体不是通过编程设定的,因此你无法预测智能体可能看到的所有情况,我们必须应对的探索空间极其庞大,而网络环境是充满敌意的,”Chrome AI 安全团队的软件工程师 Charles Qian 表示。“任何用户都可以在任何网站上提出任何提示,所以我们确实需要尽可能彻底地探索这一空间。我们已经看到,智能体开始形成成熟的判断力,知道一项任务实际需要哪些信息,以及何时应交回用户进行确认。”

搭建并填充 Mirror Dimension 本身就是一项挑战,因为它既要足够庞大和多样,以代表真实网络的规模,又要能够快速开发完成。为了构建它,Chrome 团队汇集了大量网站和网页应用开发智能体,由专门打造的 AI 框架(harness)引导,快速创建逼真的网络服务和数据流——细致到在购物网站上输入促销码,或填充社交媒体页面这样的细节。

尽管整个环境都由 Google 控制,但 Chrome 内置了太多用户保护机制和有效性校验,因此为了让智能体能够使用真实的 Chrome(这对准确的训练至关重要),研究人员实际上不得不对浏览器进行改造,并采取诸如伪造网站证书以通过有效性校验之类的复杂手段,才能让智能体获得正常的体验。不过团队强调,这些攻击手法若针对开放互联网上的普通 Chrome 用户则完全不可能奏效。它们之所以可行,全靠团队因为掌控整个环境和网络而天然拥有的“上帝模式”级别的访问权限与特权。

研究人员表示,虽然他们一直在测试的浏览助手类智能体是良性的、并不具备网络攻击能力,但他们的目标是让 Google 内部各团队都能使用 Mirror Dimension,从而让更多研究人员能够借助这个安全可控的环境开展测试。

“我们分享这一做法,是为了让内部和外部的其他团队也考虑采用这种方式,”Google 工程总监 Doug Turner 说。“这只是第一步,我们会持续投入这一训练模型的方法。而且我想,随着模型变得越来越复杂,我们将不得不持续改进这个环境,让它变得越来越真实。”

直达你的收件箱:跟随 Kernel Panic 深入数字安全世界

微软宕机事件为全世界敲响警钟

重磅报道:AI 安全辩论已经跑偏了

英国新出台的色情内容禁令引发对前所未有性审查的担忧

想要更好的搜索结果?把 WIRED 设为 Google 中的首选来源

Lily Hay Newman 是 WIRED 的高级撰稿人,关注信息安全、数字隐私和黑客技术。她此前曾在 Slate 担任科技记者,并曾担任 Future Tense 的专职撰稿人;Future Tense 是 Slate、New America Foundation 和 Arizona State University 之间的合作出版项目。她的作品…… 阅读更多

译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。

查看英文原文(Google Built a Giant ‘Mirror Dimension’ Internet to Test Its Chrome AI Agents)

The “Mirror Dimension,” which Google is detailing in a blog post today for the first time, is a sweeping and diverse but isolated web ecosystem that the Chrome team entirely controls. It includes a vast array of websites and platforms—including social media sites, shopping, and bank dashboards—that are built with all the components and attributes of real websites. Browsing assistant agents must interact with the sites and complete tasks in Chrome the way they would on the real internet. And they face resilience tests as they go, like hidden prompt-injection attacks, to test their defenses.

“Agents are not programmed so you can’t predict every possible thing an agent might see, the exploration space that we have to address is huge and the web is hostile,” says Charles Qian, a software engineer on the Chrome AI security team. “Any user can ask any prompt on any website, so we really need to explore that space as thoroughly as we can. And we’ve seen the agent start to develop a mature sense of judgement when it comes to knowing what information is actually needed for a task and when to punt back to the user for a confirmation.”

Building out and populating the Mirror Dimension was a challenge in itself, because it needed to be vast and varied enough to represent the scale of the real web while being developed quickly. To construct it, the Chrome team gathered armies of website and web app development agents guided by a purpose-built AI harness to quickly create realistic web services and data flows—down to details like entering promo codes on a shopping site or populating social media pages.

Even though the entire environment is controlled by Google, Chrome is built with so many user protections and validity checks that in order to allow the agents to use real Chrome (which is crucial for accurate training), the researchers essentially had to hack the browser and take elaborate steps like making forged web certificates for validity checks so the agents could have a normal experience. The team emphasizes, though, that none of these attacks would be possible against regular Chrome users on the open internet. They were all facilitated by the god-mode type access and privilege the team inherently has because they control the entire environment and network.

The researchers say that while the browsing assistant agents they have been testing are benign and do not have cyber capabilities, their goal is to make the Mirror Dimension available to teams across Google so more researchers have access to the safe and controlled environment for testing.

“We’re sharing this approach so other teams both internally and externally think about doing it this way,” says Doug Turner, Google’s director of engineering. “This is the first step, there’s going to be continued investment in this approach to train models. And I would imagine as they become more sophisticated we’ll have to continue working on this environment to make it more and more realistic.”

In your inbox: Go inside the world of digital security with Kernel Panic

The Microsoft outage is a warning for the world

Big Story: The AI safety debate has lost the plot

A new UK porn ban sparks fears of unprecedented sex censorship

Want better search results? Make WIRED a preferred source in Google

Lily Hay Newman is a senior writer at WIRED focused on information security, digital privacy, and hacking. She previously worked as a technology reporter at Slate, and was the staff writer for Future Tense, a publication and partnership between Slate, the New America Foundation, and Arizona State University. Her work ... Read More

原文为英文,正文由自动抓取并保留原文。

本文由采集器自动同步

原文发布于 Wired(Google Built a Giant ‘Mirror Dimension’ Internet to Test Its Chrome AI Agents),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。

阅读原文 ↗