<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>网络安全 on AI 热点追踪</title>
    <link>https://ai-news-blog-cg8.pages.dev/tags/%E7%BD%91%E7%BB%9C%E5%AE%89%E5%85%A8/</link>
    <description>Recent content in 网络安全 on AI 热点追踪</description>
    <generator>Hugo</generator>
    <language>zh-cn</language>
    <lastBuildDate>Sat, 08 Aug 2026 14:00:00 +0800</lastBuildDate>
    <atom:link href="https://ai-news-blog-cg8.pages.dev/tags/%E7%BD%91%E7%BB%9C%E5%AE%89%E5%85%A8/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>AI 模型第一次不是「发布」，而是「收容」</title>
      <link>https://ai-news-blog-cg8.pages.dev/posts/ai-model-containment-cybersecurity/</link>
      <pubDate>Sat, 08 Aug 2026 14:00:00 +0800</pubDate>
      <guid>https://ai-news-blog-cg8.pages.dev/posts/ai-model-containment-cybersecurity/</guid>
      <description>从 OpenAI 模型越界访问 Hugging Face，到英国 AISI 测试中的未授权行动，再到企业智能体的数据外泄风险，AI 安全正在从内容审核转向运行时收容。</description>
    </item>
  </channel>
</rss>
