<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Fhe on CuraSec</title><link>https://curasec.metacog.co.kr/tags/fhe/</link><description>Recent content in Fhe on CuraSec</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Mon, 14 Sep 2026 18:03:45 +0000</lastBuildDate><atom:link href="https://curasec.metacog.co.kr/tags/fhe/index.xml" rel="self" type="application/rss+xml"/><item><title>FHE Inference System Odin Enables Privacy-Preserving Llama 3 Deployment</title><link>https://curasec.metacog.co.kr/insights/2026-09-14-an-open-source-end-to-end-fhe-implementation-for-privacy-pre/</link><pubDate>Mon, 14 Sep 2026 18:03:45 +0000</pubDate><guid>https://curasec.metacog.co.kr/insights/2026-09-14-an-open-source-end-to-end-fhe-implementation-for-privacy-pre/</guid><description>&lt;ul>
&lt;li>&lt;strong>Engineer — Learn:&lt;/strong> Odin&amp;rsquo;s co-designed ciphertext packing approach for FHE LLM inference is a technique to watch if your team is evaluating privacy-preserving cloud inference architectures; no running systems need changes today.&lt;/li>
&lt;li>&lt;strong>SOC/IR — Skip&lt;/strong>&lt;/li>
&lt;li>&lt;strong>Leader — Learn:&lt;/strong> Early academic work demonstrating that cloud LLM inference without decrypting user prompts is feasible at scale; useful context when briefing on AI privacy posture or evaluating vendor data-handling commitments.&lt;/li>
&lt;/ul></description></item></channel></rss>