<?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>模型保护 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%A8%A1%E5%9E%8B%E4%BF%9D%E6%8A%A4/</link><description>Recent content in 模型保护 on 硅基 AGI · 智能体学习与测评</description><generator>Hugo</generator><language>zh-cn</language><copyright>本站内容采用 CC BY-NC-SA 4.0 国际许可协议授权</copyright><lastBuildDate>Sun, 28 Jun 2026 11:30:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%A8%A1%E5%9E%8B%E4%BF%9D%E6%8A%A4/index.xml" rel="self" type="application/rss+xml"/><item><title>模型窃取攻击与防御：保护你的模型权重</title><link>https://guijiagi.com/posts/model-stealing-attacks-defense/</link><pubDate>Sun, 28 Jun 2026 11:30:00 +0800</pubDate><guid>https://guijiagi.com/posts/model-stealing-attacks-defense/</guid><description>LLM模型窃取攻击的完整分析：从API提取到侧信道攻击及防御策略</description></item></channel></rss>