<?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>保护 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E4%BF%9D%E6%8A%A4/</link><description>Recent content in 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>Sat, 27 Jun 2026 15:00:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E4%BF%9D%E6%8A%A4/index.xml" rel="self" type="application/rss+xml"/><item><title>Agent数据隐私保护方案</title><link>https://guijiagi.com/posts/agent-data-privacy-protection/</link><pubDate>Sat, 27 Jun 2026 15:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/agent-data-privacy-protection/</guid><description>Agent数据隐私保护方案</description></item><item><title>Prompt 泄露防护：别让你的核心 Prompt 被提取</title><link>https://guijiagi.com/posts/prompt-leakage-protection/</link><pubDate>Thu, 25 Jun 2026 10:00:00 +0800</pubDate><guid>https://guijiagi.com/posts/prompt-leakage-protection/</guid><description>深入解析 Prompt 提取攻击原理、真实泄露案例、多层防御策略（指令层级、分隔符、检测、混淆）及评估方法。</description></item></channel></rss>