<?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>模型提取 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%A8%A1%E5%9E%8B%E6%8F%90%E5%8F%96/</link><description>Recent content in 模型提取 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>Thu, 02 Jul 2026 10:24:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%A8%A1%E5%9E%8B%E6%8F%90%E5%8F%96/index.xml" rel="self" type="application/rss+xml"/><item><title>AI模型窃取与防范：保护模型知识产权的攻防战</title><link>https://guijiagi.com/posts/ai-model-stealing-prevention/</link><pubDate>Thu, 02 Jul 2026 10:24:00 +0800</pubDate><guid>https://guijiagi.com/posts/ai-model-stealing-prevention/</guid><description>系统探讨AI模型窃取攻击的手法、影响与防范措施，保护模型知识产权</description></item><item><title>模型隐私攻击与防护：你的模型在泄露什么？</title><link>https://guijiagi.com/posts/model-privacy-attacks/</link><pubDate>Wed, 24 Jun 2026 14:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/model-privacy-attacks/</guid><description>系统介绍 LLM 隐私攻击技术，涵盖成员推断攻击、模型提取攻击、训练数据提取及差分隐私等防护手段</description></item></channel></rss>