<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Machine Learning on Vivian＠資安媽媽包</title><link>https://vvnblog.com/tags/machine-learning/</link><description>Recent content in Machine Learning on Vivian＠資安媽媽包</description><generator>Hugo -- gohugo.io</generator><language>zh-tw</language><copyright>Copyright © 2026 Vivian All Rights Reserved.</copyright><lastBuildDate>Thu, 10 Sep 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://vvnblog.com/tags/machine-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>AI 黑魔法（22）：從源頭下毒到藏後門，資料投毒與後門模型</title><link>https://vvnblog.com/posts/ai-dark-arts-22/</link><pubDate>Thu, 10 Sep 2026 00:00:00 +0800</pubDate><guid>https://vvnblog.com/posts/ai-dark-arts-22/</guid><description>資料投毒在訓練、微調或回饋流程中改變模型所學的規則；後門則讓污染結果只在特定 Trigger 出現時發作，兩者是一條從教材到模型行為的因果鏈。</description></item></channel></rss>