<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Jailbreak Defense | Yiqiao Jin CS PhD @ Georgia Tech</title><link>https://ahren09.github.io/tags/jailbreak-defense/</link><atom:link href="https://ahren09.github.io/tags/jailbreak-defense/index.xml" rel="self" type="application/rss+xml"/><description>Jailbreak Defense</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Mon, 03 Mar 2025 00:00:00 +0000</lastBuildDate><image><url>https://ahren09.github.io/media/icon_hu_eee6347cbdb2cc3f.png</url><title>Jailbreak Defense</title><link>https://ahren09.github.io/tags/jailbreak-defense/</link></image><item><title>UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models</title><link>https://ahren09.github.io/publication/aaai25_uniguard/</link><pubDate>Mon, 03 Mar 2025 00:00:00 +0000</pubDate><guid>https://ahren09.github.io/publication/aaai25_uniguard/</guid><description>&lt;h2 id="abstract">Abstract&lt;/h2>
&lt;p>Multimodal LLMs are vulnerable to jailbreak attacks that exploit cross-modal interactions. We introduce UniGuard, a universal safety guardrail framework that defends multimodal LLMs against jailbreak attacks across image and text channels.&lt;/p>
&lt;h2 id="links">Links&lt;/h2>
&lt;ul>
&lt;li>
&lt;/li>
&lt;/ul></description></item></channel></rss>