<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
	>

<channel>
	<title>Sumit Jha &#8211; UF Innovate</title>
	<atom:link href="https://innovate.research.ufl.edu/tag/sumit-jha/feed/" rel="self" type="application/rss+xml" />
	<link>https://innovate.research.ufl.edu</link>
	<description>Building business on innovation</description>
	<lastBuildDate>Mon, 23 Feb 2026 19:53:36 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	<generator>https://wordpress.org/?v=6.9.4</generator>

<image>
	<url>https://innovate.research.ufl.edu/wp-content/uploads/favicon-blue_1.png</url>
	<title>Sumit Jha &#8211; UF Innovate</title>
	<link>https://innovate.research.ufl.edu</link>
	<width>32</width>
	<height>32</height>
</image> 
	<item>
		<title>Breaking AI on Purpose: How Researchers Are Helping Make Artificial Intelligence Safer (UF News)</title>
		<link>https://innovate.research.ufl.edu/breaking-ai/</link>
		
		<dc:creator><![CDATA[sooyoungryu]]></dc:creator>
		<pubDate>Mon, 23 Feb 2026 19:53:36 +0000</pubDate>
				<category><![CDATA[News Brief]]></category>
		<category><![CDATA[AI]]></category>
		<category><![CDATA[artificial intelligence]]></category>
		<category><![CDATA[HiPerGator]]></category>
		<category><![CDATA[internal defenses]]></category>
		<category><![CDATA[security]]></category>
		<category><![CDATA[Sumit Jha]]></category>
		<category><![CDATA[Sumit Kumar Jha]]></category>
		<guid isPermaLink="false">https://innovate.research.ufl.edu/?p=21713</guid>

					<description><![CDATA[UF researcher Sumit Kumar Jha developed a novel method to probe and stress test AI systems’ internal defenses, revealing security gaps and advancing safer deployment of AI tools, with the work accepted to ICLR 2026.]]></description>
										<content:encoded><![CDATA[<p>Nullspace steering. Red teaming. Jailbreaking the matrix.</p>
<p>A paper written by University of Florida Computer &amp; Information Science &amp; Engineering, or CISE, Professor Sumit Kumar Jha, Ph.D., contains so many science fiction terms, you’d be forgiven for thinking it’s a Hollywood script.</p>
<p>But Jha’s work is decidedly focused on real life, most notably strengthening the security measures built into AI tools to ensure they are safe for all to use.</p>
<p>&nbsp;</p>
<p>Read more about <a href="https://news.ufl.edu/2026/02/breaking-ai/">Breaking AI on Purpose: How Researchers Are Helping Make Artificial Intelligence Safer.</a></p>
]]></content:encoded>
					
		
		
			</item>
	</channel>
</rss>
