<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Llm on XoanOuteiro's Cybersec Notes</title><link>https://xoanouteiro.dev/tags/llm/</link><description>Recent content in Llm on XoanOuteiro's Cybersec Notes</description><generator>Hugo -- 0.142.0</generator><language>en-us</language><lastBuildDate>Sat, 26 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://xoanouteiro.dev/tags/llm/index.xml" rel="self" type="application/rss+xml"/><item><title>Exploring probabilistic classifier bypasses via prompt padding.</title><link>https://xoanouteiro.dev/posts/exploring_probabilistic_request_padding/</link><pubDate>Sat, 26 Sep 2026 00:00:00 +0000</pubDate><guid>https://xoanouteiro.dev/posts/exploring_probabilistic_request_padding/</guid><description>A theory on how we may see the rise of prompt padding in LLM attacks.</description></item></channel></rss>