<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Adversarial ML on AI VOID</title><link>https://ai-blog.noorshomelab.dev/tags/adversarial-ml/</link><description>Recent content in Adversarial ML on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Fri, 20 Mar 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/tags/adversarial-ml/index.xml" rel="self" type="application/rss+xml"/><item><title>Data Poisoning: Corrupting the AI&amp;#39;s Brain</title><link>https://ai-blog.noorshomelab.dev/ai-security-guide-2026/data-poisoning/</link><pubDate>Fri, 20 Mar 2026 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/ai-security-guide-2026/data-poisoning/</guid><description>&lt;h2 id="introduction-the-silent-saboteur-of-ai"&gt;Introduction: The Silent Saboteur of AI&lt;/h2&gt;
&lt;p&gt;Welcome back, future AI security champions! In our previous chapters, we delved into the immediate threats of prompt injection and jailbreak attacks, where adversaries manipulate an AI model&amp;rsquo;s behavior &lt;em&gt;during runtime&lt;/em&gt;. But what if the problem starts much earlier, deep within the very &amp;ldquo;brain&amp;rdquo; of the AI itself?&lt;/p&gt;
&lt;p&gt;This chapter introduces you to &lt;strong&gt;Data Poisoning&lt;/strong&gt;, a sinister attack where malicious actors inject corrupted data into an AI model&amp;rsquo;s training or fine-tuning datasets. Imagine trying to teach a student using a textbook filled with subtle, misleading errors. Over time, these errors would warp their understanding, leading to incorrect responses and potentially dangerous decisions. That&amp;rsquo;s precisely what data poisoning does to an AI.&lt;/p&gt;</description></item></channel></rss>