<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0"><channel><title><![CDATA[Phishing / spam detection with local LLMs?]]></title><description><![CDATA[<p dir="auto">I've tried giving screenshots of phishing emails to a local Qwen instance and so far it always correctly detected it as scam, even points out the exact elements that it based its judgement on. Sending screenshots to it ad-hoc isn't too scalable for family and friends. I'd like to be able to either forward emails for screening, or perhaps have it screen everything from a mailbox.</p>
<p dir="auto">Has anyone done anything like this? Is there anything self-hostable that does this?</p>
]]></description><link>https://forum.ieu.app/topic/c2d7a58a-7f0a-43b5-9ef7-22db3ebb8d6b/phishing-spam-detection-with-local-llms</link><generator>RSS for Node</generator><lastBuildDate>Thu, 22 Oct 2026 01:52:47 GMT</lastBuildDate><atom:link href="https://forum.ieu.app/topic/c2d7a58a-7f0a-43b5-9ef7-22db3ebb8d6b.rss" rel="self" type="application/rss+xml"/><pubDate>Mon, 28 Sep 2026 21:57:20 GMT</pubDate><ttl>60</ttl></channel></rss>