<?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 Cyberpal.AI:  Empowering LLMs with Expert-Driven Cybersecurity Instructions in Tech Talk</title>
    <link>https://community.isc2.org/t5/Tech-Talk/Cyberpal-AI-Empowering-LLMs-with-Expert-Driven-Cybersecurity/m-p/73340#M4536</link>
    <description>&lt;P&gt;Hi All&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;An interesting insight:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&lt;SPAN&gt;We all know LLMs are great, but they often struggle with complex, domain-specific tasks such as cybersecurity-related tasks (i.e., threat intelligence). In this study, we introduce SecKnowledge and CyberPal. AI to address these challenges and train security-expert LLMs.&lt;BR /&gt;&lt;BR /&gt;We construct SecKnowledge, an instruction-tuning dataset generated using an expert-driven process on a wide range of security-related datasets.&lt;BR /&gt;The dataset construction involves two main steps:&lt;BR /&gt;In the first step, we create instructions based on predefined schemas established through domain expertise. These schemas define templates that are filled with domain expert knowledge and supplemented with LLM-generated content when necessary.&lt;BR /&gt;In the second step, we expand the initial dataset through a hybrid synthetic content-based data generation process.&lt;BR /&gt;&lt;BR /&gt;Then, we train CyberPal. AI, a family of cyber-security expert LLMs, capable of understanding complex security concepts. CyberPal. AI demonstrates the advantages of enhancing LLMs with our domain-knowledge instruction dataset, SecKnowledge.&lt;BR /&gt;&lt;BR /&gt;Lastly, we developed SecKnowledge-Eval, a suite of evaluation datasets specifically designed to assess LLMs in the cyber-security domain. SecKnowledge-Eval consists of evaluation datasets we constructed to assess LLMs’ capabilities on complex cyber-security tasks, alongside public benchmarks, intending to generate a comprehensive and diverse evaluation dataset.&lt;BR /&gt;&lt;BR /&gt;CyberPal. AI demonstrated superior performance over its baseline models, showing a substantial average improvement of up to 24% in training-aligned tasks and up to 10% in public cyber-security benchmarks.&lt;BR /&gt;&lt;BR /&gt;Check out our approach here: &lt;A class="" href="https://lnkd.in/dn-QfSFB" target="_self"&gt;https://lnkd.in/dn-QfSFB&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&lt;SPAN&gt;See attached:&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;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Fri, 23 Aug 2024 05:53:54 GMT</pubDate>
    <dc:creator>Caute_cautim</dc:creator>
    <dc:date>2024-08-23T05:53:54Z</dc:date>
    <item>
      <title>Cyberpal.AI:  Empowering LLMs with Expert-Driven Cybersecurity Instructions</title>
      <link>https://community.isc2.org/t5/Tech-Talk/Cyberpal-AI-Empowering-LLMs-with-Expert-Driven-Cybersecurity/m-p/73340#M4536</link>
      <description>&lt;P&gt;Hi All&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;An interesting insight:&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&lt;SPAN&gt;We all know LLMs are great, but they often struggle with complex, domain-specific tasks such as cybersecurity-related tasks (i.e., threat intelligence). In this study, we introduce SecKnowledge and CyberPal. AI to address these challenges and train security-expert LLMs.&lt;BR /&gt;&lt;BR /&gt;We construct SecKnowledge, an instruction-tuning dataset generated using an expert-driven process on a wide range of security-related datasets.&lt;BR /&gt;The dataset construction involves two main steps:&lt;BR /&gt;In the first step, we create instructions based on predefined schemas established through domain expertise. These schemas define templates that are filled with domain expert knowledge and supplemented with LLM-generated content when necessary.&lt;BR /&gt;In the second step, we expand the initial dataset through a hybrid synthetic content-based data generation process.&lt;BR /&gt;&lt;BR /&gt;Then, we train CyberPal. AI, a family of cyber-security expert LLMs, capable of understanding complex security concepts. CyberPal. AI demonstrates the advantages of enhancing LLMs with our domain-knowledge instruction dataset, SecKnowledge.&lt;BR /&gt;&lt;BR /&gt;Lastly, we developed SecKnowledge-Eval, a suite of evaluation datasets specifically designed to assess LLMs in the cyber-security domain. SecKnowledge-Eval consists of evaluation datasets we constructed to assess LLMs’ capabilities on complex cyber-security tasks, alongside public benchmarks, intending to generate a comprehensive and diverse evaluation dataset.&lt;BR /&gt;&lt;BR /&gt;CyberPal. AI demonstrated superior performance over its baseline models, showing a substantial average improvement of up to 24% in training-aligned tasks and up to 10% in public cyber-security benchmarks.&lt;BR /&gt;&lt;BR /&gt;Check out our approach here: &lt;A class="" href="https://lnkd.in/dn-QfSFB" target="_self"&gt;https://lnkd.in/dn-QfSFB&lt;/A&gt;&lt;BR /&gt;&lt;BR /&gt;&lt;/SPAN&gt;&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN class=""&gt;&lt;SPAN&gt;See attached:&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;&lt;P&gt;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Fri, 23 Aug 2024 05:53:54 GMT</pubDate>
      <guid>https://community.isc2.org/t5/Tech-Talk/Cyberpal-AI-Empowering-LLMs-with-Expert-Driven-Cybersecurity/m-p/73340#M4536</guid>
      <dc:creator>Caute_cautim</dc:creator>
      <dc:date>2024-08-23T05:53:54Z</dc:date>
    </item>
  </channel>
</rss>

