<?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>数据投毒 on 硅基 AGI · 智能体学习与测评</title><link>https://guijiagi.com/tags/%E6%95%B0%E6%8D%AE%E6%8A%95%E6%AF%92/</link><description>Recent content in 数据投毒 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 10:23:00 +0800</lastBuildDate><atom:link href="https://guijiagi.com/tags/%E6%95%B0%E6%8D%AE%E6%8A%95%E6%AF%92/index.xml" rel="self" type="application/rss+xml"/><item><title>AI数据投毒攻防2026：保护模型训练的纯净性</title><link>https://guijiagi.com/posts/ai-data-poisoning-2026/</link><pubDate>Thu, 02 Jul 2026 10:23:00 +0800</pubDate><guid>https://guijiagi.com/posts/ai-data-poisoning-2026/</guid><description>深入探讨2026年AI数据投毒攻击的最新手法、检测方法与防御策略</description></item><item><title>数据投毒攻击：训练数据安全的隐形威胁</title><link>https://guijiagi.com/posts/data-poisoning-attacks/</link><pubDate>Sun, 28 Jun 2026 11:25:00 +0800</pubDate><guid>https://guijiagi.com/posts/data-poisoning-attacks/</guid><description>深入解析LLM数据投毒攻击：从投毒手法到检测防御的完整方案</description></item></channel></rss>