<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Threat Modeling for LLM-Powered Applications in Tech Talk</title>
    <link>https://community.isc2.org/t5/Tech-Talk/Threat-Modeling-for-LLM-Powered-Applications/m-p/71600#M4458</link>
    <description>&lt;P&gt;Hi All&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&lt;SPAN&gt;There's no denying we're seeing explosive adoption of GenAI and LLM use cases and applications&lt;BR /&gt;&lt;BR /&gt;That said, it's not too late for organizations to utilize one of the best secure software development methodologies out there, Threat Modeling to ensure secure adoption of LLM's.&lt;BR /&gt;&lt;BR /&gt;This is an excellent paper discussing "Threat Modeling and Risk Analysis for LLM-Powered Applications"&lt;BR /&gt;&lt;BR /&gt;It covers:&lt;BR /&gt;&lt;BR /&gt;- Potential attacks against LLM-powered applications and their potential impacts&lt;BR /&gt;&lt;BR /&gt;- LLM specific attack vectors and risks&lt;BR /&gt;&lt;BR /&gt;- Widely used Threat Modeling methodologies and adapting them for LLM applications (cc: &lt;A class="" href="https://www.linkedin.com/in/shostack/" target="_blank" rel="noopener"&gt;&lt;span class="lia-unicode-emoji" title=":face_with_medical_mask:"&gt;😷&lt;/span&gt; Adam Shostack&lt;/A&gt;&lt;/SPAN&gt;)&lt;SPAN&gt;&lt;BR /&gt;&lt;/SPAN&gt;&lt;SPAN&gt;&lt;BR /&gt;&lt;/SPAN&gt;- An example LLM-application threat model&lt;SPAN&gt;&lt;BR /&gt;&lt;/SPAN&gt;&lt;SPAN&gt;&lt;BR /&gt;&lt;/SPAN&gt;Definitely a key activity organizations should be having their security, development and engineering teams implement as they move forward adopting LLM and GenAI use cases for organizational outcomes, and doing so securely.&lt;SPAN&gt;&lt;BR /&gt;&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&lt;SPAN&gt;Regards&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&lt;SPAN&gt;Caute_Cautim&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/P&gt;</description>
    <pubDate>Sun, 30 Jun 2024 22:54:24 GMT</pubDate>
    <dc:creator>Caute_cautim</dc:creator>
    <dc:date>2024-06-30T22:54:24Z</dc:date>
    <item>
      <title>Threat Modeling for LLM-Powered Applications</title>
      <link>https://community.isc2.org/t5/Tech-Talk/Threat-Modeling-for-LLM-Powered-Applications/m-p/71600#M4458</link>
      <description>&lt;P&gt;Hi All&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&lt;SPAN&gt;There's no denying we're seeing explosive adoption of GenAI and LLM use cases and applications&lt;BR /&gt;&lt;BR /&gt;That said, it's not too late for organizations to utilize one of the best secure software development methodologies out there, Threat Modeling to ensure secure adoption of LLM's.&lt;BR /&gt;&lt;BR /&gt;This is an excellent paper discussing "Threat Modeling and Risk Analysis for LLM-Powered Applications"&lt;BR /&gt;&lt;BR /&gt;It covers:&lt;BR /&gt;&lt;BR /&gt;- Potential attacks against LLM-powered applications and their potential impacts&lt;BR /&gt;&lt;BR /&gt;- LLM specific attack vectors and risks&lt;BR /&gt;&lt;BR /&gt;- Widely used Threat Modeling methodologies and adapting them for LLM applications (cc: &lt;A class="" href="https://www.linkedin.com/in/shostack/" target="_blank" rel="noopener"&gt;&lt;span class="lia-unicode-emoji" title=":face_with_medical_mask:"&gt;😷&lt;/span&gt; Adam Shostack&lt;/A&gt;&lt;/SPAN&gt;)&lt;SPAN&gt;&lt;BR /&gt;&lt;/SPAN&gt;&lt;SPAN&gt;&lt;BR /&gt;&lt;/SPAN&gt;- An example LLM-application threat model&lt;SPAN&gt;&lt;BR /&gt;&lt;/SPAN&gt;&lt;SPAN&gt;&lt;BR /&gt;&lt;/SPAN&gt;Definitely a key activity organizations should be having their security, development and engineering teams implement as they move forward adopting LLM and GenAI use cases for organizational outcomes, and doing so securely.&lt;SPAN&gt;&lt;BR /&gt;&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&lt;SPAN&gt;Regards&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&lt;SPAN&gt;Caute_Cautim&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Sun, 30 Jun 2024 22:54:24 GMT</pubDate>
      <guid>https://community.isc2.org/t5/Tech-Talk/Threat-Modeling-for-LLM-Powered-Applications/m-p/71600#M4458</guid>
      <dc:creator>Caute_cautim</dc:creator>
      <dc:date>2024-06-30T22:54:24Z</dc:date>
    </item>
  </channel>
</rss>

