<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Model-Poisoning on i break software - My work with different software, bug hunting and interesting tidbits.</title>
    <link>/categories/model-poisoning/</link>
    <description>Recent content in Model-Poisoning on i break software - My work with different software, bug hunting and interesting tidbits.</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Tue, 17 Nov 2026 05:14:55 +0530</lastBuildDate>
    <atom:link href="/categories/model-poisoning/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>One Ticket ID, One Calculator: Backdooring a Local LLM for OWASP LLM04</title>
      <link>/2026/11/backdooring-a-local-llm-model-poisoning-llm04/</link>
      <pubDate>Tue, 17 Nov 2026 05:00:00 +0530</pubDate>
      <guid>/2026/11/backdooring-a-local-llm-model-poisoning-llm04/</guid>
      <description>&lt;p&gt;A working Proof of Concept for OWASP LLM04: Data and Model Poisoning, built end to end on a laptop. I poison a dataset, fine-tune a backdoor into an open weights model, merge the adapter, ship it as a GGUF through Ollama, and have a tool-calling agent run a command the user never asked for.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
