arXiv cs.CL· William Fleshman, Joseph Lucas·· 10 小时前AI 评分58
研究揭示 Chrome 内置 Gemini Nano 可被滥用为后渗透引擎
Living off the Local Model: Abusing Browser-Embedded Language Models for Post-Exploitation
AI 导读
arXiv 论文研究显示,Chrome 内置的 Gemini Nano 可仅用操作系统自带解释器从主机侧驱动,下载前的一次性用户激活检查也能通过模拟点击满足或绕过。作者测试了该模型在主机上识别凭证、检测邮件中的 PII、分类图像和调用自定义工具的能力,并串联这些能力完成一次模拟攻击:从摄像头图像读取密码、解锁加密压缩包、分拣内容并暂存私钥待外传,全程无需用户交互。
正文 · 原文
Abstract:Browsers now ship local language models to ordinary endpoints. Google includes Gemini Nano in Chrome to enable productivity features such as summarization, with inference running entirely on the device. These browser-embedded models provide new living-off-the-land opportunities for attackers, each instance a potential post-exploitation engine already installed, signed by the vendor, and invisible to network monitoring. The Gemini model is multimodal, capable of processing files, analyzing screenshots, or conversing with an attacker. We show that it can be driven from the host using only interpreters that ship with the operating system and find that the one-time user-activation check before the model is downloaded is easily satisfied with a simulated click or bypassed this http URL measure and report the current model's ability to identify credentials on the host, detect PII in email, classify images, and call custom tools. We combine these capabilities and use the model to carry out a simulated cyber operation: reading a password from a webcam image, unlocking an encrypted archive, triaging the contents, and staging a private key for exfiltration, end-to-end without user-interaction.
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.25086 [cs.CR] |
| (or arXiv:2611.25086v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.25086 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: William Fleshman [view email]
[v1]
Wed, 18 Nov 2026 19:23:44 UTC (183 KB)
来源:arXiv cs.CL · arxiv.org