<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Inference API on Vivian＠資安媽媽包</title><link>https://vvnblog.com/tags/inference-api/</link><description>Recent content in Inference API 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>Tue, 08 Sep 2026 00:00:00 +0800</lastBuildDate><atom:link href="https://vvnblog.com/tags/inference-api/index.xml" rel="self" type="application/rss+xml"/><item><title>AI 黑魔法（20）：模型服務正常運作，帳單、資料與 Host 怎麼還是出事了？</title><link>https://vvnblog.com/posts/ai-dark-arts-20/</link><pubDate>Tue, 08 Sep 2026 00:00:00 +0800</pubDate><guid>https://vvnblog.com/posts/ai-dark-arts-20/</guid><description>拆解 LLMjacking、Tenant 資料外洩與 GPU Runtime 漏洞，找出模型服務該在哪裡限成本、拆權限與做隔離。</description></item></channel></rss>