<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Rag on CuraSec</title><link>https://curasec.metacog.co.kr/tags/rag/</link><description>Recent content in Rag on CuraSec</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 03 Aug 2026 15:12:30 +0000</lastBuildDate><atom:link href="https://curasec.metacog.co.kr/tags/rag/index.xml" rel="self" type="application/rss+xml"/><item><title>GoldenRetriever: Homomorphic Encrypted Retrieval for Private RAG</title><link>https://curasec.metacog.co.kr/insights/2026-08-03-goldenretriever-non-interactive-homomorphic-encrypted-retrie/</link><pubDate>Mon, 03 Aug 2026 15:12:30 +0000</pubDate><guid>https://curasec.metacog.co.kr/insights/2026-08-03-goldenretriever-non-interactive-homomorphic-encrypted-retrie/</guid><description>&lt;ul>
&lt;li>&lt;strong>Engineer — Learn:&lt;/strong> Introduces a CKKS-based non-interactive encrypted retrieval framework for RAG that cuts complexity from quadratic to linear; worth tracking if you&amp;rsquo;re building privacy-preserving AI pipelines, but no production library or patch to apply today.&lt;/li>
&lt;li>&lt;strong>SOC/IR — Skip&lt;/strong>&lt;/li>
&lt;li>&lt;strong>Leader — Learn:&lt;/strong> Demonstrates a practical path toward fully encrypted RAG pipelines, relevant if you&amp;rsquo;re evaluating AI product privacy posture or responding to customer questions about LLM data exposure.&lt;/li>
&lt;/ul></description></item></channel></rss>