论文精选

BrowseSafe:保护浏览器代理免受提示注入的开源基准

And open sourced BrowseSafe, an open benchmark for protecting agents against prompt injection on web...

精选理由

BrowseSafe开源了,专门测浏览器代理防提示注入的能力,做安全测试的可以看看。

AI 摘要

BrowseSafe是一个开源基准,用于评估代理对提示注入攻击的防御能力。它模拟代理在浏览器会话中访问网站时的实际场景。该基准旨在推动更安全的浏览器代理开发。

图片来源 · Aravind Srinivas
原文 · Aravind Srinivas

And open sourced BrowseSafe, an open benchmark for protecting agents against prompt injection on web...

And open sourced BrowseSafe, an open benchmark for protecting agents against prompt injection on websites they access on a web browser session arxiv.org/abs/2511.20597 💬 1 🔄 1 ❤️ 9 👀 1721 📊 2 ⚡