为智能浏览器设计安全机制，防止跨域数据泄露。
Same-Origin Policy for Agentic Browsers
- 提出SOPGuard机制，专用于智能浏览器的同源策略防护。
- 测试显示现有智能浏览器频繁违反同源策略，存在安全漏洞。
- 在保持功能实用性的前提下，仅增加少量运行开销。
智能浏览器将自主AI代理集成到网页浏览器中，使用户可通过自然语言指令完成网络任务。同源策略（SOP）是浏览器的一项基本安全机制，用于阻止脚本引发的未经授权的跨域数据流动。然而，当智能浏览器本身成为自动化跨域数据流的渠道时，现有SOP的有效性尚不明确。本文首次系统研究此问题，发现智能浏览器可能成为跨域数据泄露的自动化通道。为此，我们构建了SOPBench——一个评估智能浏览器中SOP违规行为的基准测试集。实验表明，现有智能浏览器在正常场景和攻击条件下均频繁违反SOP。为应对该问题，我们提出SOPGuard，一种专为智能浏览器设计的同源策略强制机制。我们在开源智能浏览器BrowserOS中实现了SOPGuard。大量评估结果显示，SOPGuard能有效执行同源策略，同时保持任务实用性，且仅带来轻微的运行时开销。相关代码与数据已公开于https://github.com/wxl-lxw/BrowserOS-SOPGuard。
原文摘要 · Abstract (English)
Agentic browsers integrate autonomous AI agents into web browsers, enabling users to accomplish web tasks through natural-language instructions. The same-origin policy (SOP) is a fundamental browser security mechanism that prevents unauthorized automated cross-origin data flows induced by scripts. However, whether SOP remains effective in agentic browsers is an open question that has not been systematically studied. In this work, we bridge this gap. We first observe that an agentic browser can itself serve as an automated channel for cross-origin data flows, potentially leading to SOP violations. To investigate this phenomenon, we construct SOPBench, a benchmark for evaluating SOP violations in agentic browsers. Our evaluation shows that existing agentic browsers frequently violate SOP, both in benign settings and under attacks. To address this problem, we propose SOPGuard, an SOP enforcement mechanism tailored to agentic browsers. We implement SOPGuard in BrowserOS, an open-source agentic browser. Extensive evaluations demonstrate that SOPGuard effectively enforces SOP while preserving utility and incurring only a small runtime overhead. Our code and data are available at https://github.com/wxl-lxw/BrowserOS-SOPGuard.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。