<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>AI on My AWS Rocks!</title><link>https://www.myaws.rocks/tags/ai/</link><description>Recent content in AI on My AWS Rocks!</description><generator>Hugo</generator><language>en</language><lastBuildDate>Tue, 01 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://www.myaws.rocks/tags/ai/index.xml" rel="self" type="application/rss+xml"/><item><title>Security at Depth - AI</title><link>https://www.myaws.rocks/security-at-depth-ai/</link><pubDate>Tue, 01 Sep 2026 00:00:00 +0000</pubDate><guid>https://www.myaws.rocks/security-at-depth-ai/</guid><description>&lt;p&gt;Artificial intelligence is becoming a source of value and a new concentration of risk. Models can expose sensitive information, amplify unsafe instructions, create convincing but incorrect output, or be manipulated through their data, tools and interfaces. Securing AI therefore means protecting more than an algorithm: it means controlling the complete system around it.&lt;/p&gt;
&lt;p&gt;This post in a series on &lt;a href="https://www.myaws.rocks/security-at-all-levels/"&gt;security at all layers&lt;/a&gt; focuses on AI security. I&amp;rsquo;ll look at protection across three stages: Foundations, Development, and Deployment, and in three ways: Governance, Protection, and Resilience.&lt;/p&gt;</description></item></channel></rss>