<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Applied Cryptography |</title><link>http://darrylab.org/tags/applied-cryptography/</link><atom:link href="http://darrylab.org/tags/applied-cryptography/index.xml" rel="self" type="application/rss+xml"/><description>Applied Cryptography</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Tue, 01 Sep 2026 00:00:00 +0000</lastBuildDate><image><url>http://darrylab.org/media/icon_hu_1c0e9cb08cfb822a.png</url><title>Applied Cryptography</title><link>http://darrylab.org/tags/applied-cryptography/</link></image><item><title>Trust for AI Agents Offline</title><link>http://darrylab.org/projects/agent-attestation/</link><pubDate>Tue, 01 Sep 2026 00:00:00 +0000</pubDate><guid>http://darrylab.org/projects/agent-attestation/</guid><description>&lt;p&gt;AI agents increasingly call tools, APIs and other agents on our behalf. Today&amp;rsquo;s identity and trust frameworks assume an agent can always reach a server to check credentials, an assumption that breaks in much of the world.&lt;/p&gt;
&lt;p&gt;This project develops a lightweight attestation protocol that lets agents prove where a tool call came from and verify it locally, so trust holds even on intermittent networks. It targets the resource constrained deployments common across Africa and other emerging regions.&lt;/p&gt;
&lt;p&gt;Full working title: &lt;em&gt;Lightweight Attestation Based Provenance Verification for Autonomous AI Agent Tool Invocation: A Connectivity Resilient Trust Protocol for Resource Constrained AI Deployments.&lt;/em&gt;&lt;/p&gt;
&lt;p&gt;&lt;strong&gt;Status:&lt;/strong&gt; Ongoing research.&lt;/p&gt;</description></item></channel></rss>