cai/benchmarking/knowledge_benchmarks/index.html

3571 lines
74 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="prev" href="../cyber_ranges/">
<link rel="next" href="../privacy_benchmarks/">
<link rel="icon" href="../../assets/imago.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.11">
<title>Knowledge Benchmarks - CAI</title>
<link rel="stylesheet" href="../../assets/stylesheets/main.4af4bdda.min.css">
<link rel="stylesheet" href="../../assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<link rel="stylesheet" href="../../assets/_mkdocstrings.css">
<link rel="stylesheet" href="../../stylesheets/extra.css">
<script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="custom" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#knowledge-benchmarks" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href="../.." title="CAI" class="md-header__button md-logo" aria-label="CAI" data-md-component="logo">
<img src="../../assets/imago.png" alt="logo">
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
CAI
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Knowledge Benchmarks
</span>
</div>
</div>
</div>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/aliasrobotics/cai" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8M97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</div>
<div class="md-source__repository">
aliasrobotics/cai
</div>
</a>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href="../.." title="CAI" class="md-nav__button md-logo" aria-label="CAI" data-md-component="logo">
<img src="../../assets/imago.png" alt="logo">
</a>
CAI
</label>
<div class="md-nav__source">
<a href="https://github.com/aliasrobotics/cai" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 496 512"><!--! Font Awesome Free 6.7.2 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M165.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M244.8 8C106.1 8 0 113.3 0 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C428.2 457.8 496 362.9 496 252 496 113.3 383.5 8 244.8 8M97.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</div>
<div class="md-source__repository">
aliasrobotics/cai
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_1" >
<label class="md-nav__link" for="__nav_1" id="__nav_1_label" tabindex="">
<span class="md-ellipsis">
Getting Started
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_1">
<span class="md-nav__icon md-icon"></span>
Getting Started
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../.." class="md-nav__link">
<span class="md-ellipsis">
Welcome
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cai_installation/" class="md-nav__link">
<span class="md-ellipsis">
Installation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cai_quickstart/" class="md-nav__link">
<span class="md-ellipsis">
Quickstart
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cai_list_of_models/" class="md-nav__link">
<span class="md-ellipsis">
Available Models
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_1_5" >
<label class="md-nav__link" for="__nav_1_5" id="__nav_1_5_label" tabindex="0">
<span class="md-ellipsis">
Model Providers
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_1_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_1_5">
<span class="md-nav__icon md-icon"></span>
Model Providers
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../providers/openrouter.md" class="md-nav__link">
<span class="md-ellipsis">
OpenRouter
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../providers/ollama/" class="md-nav__link">
<span class="md-ellipsis">
Ollama
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../providers/azure.md" class="md-nav__link">
<span class="md-ellipsis">
Azure OpenAI
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../../cai_pro/" class="md-nav__link">
<span class="md-ellipsis">
🚀 CAI PRO
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_3" >
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="">
<span class="md-ellipsis">
Core Concepts
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
Core Concepts
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../cai_architecture/" class="md-nav__link">
<span class="md-ellipsis">
Architecture
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../agents/" class="md-nav__link">
<span class="md-ellipsis">
Agents
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tools/" class="md-nav__link">
<span class="md-ellipsis">
Tools
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../handoffs/" class="md-nav__link">
<span class="md-ellipsis">
Handoffs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../multi_agent/" class="md-nav__link">
<span class="md-ellipsis">
Multi-Agent Systems
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--active md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" checked>
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="">
<span class="md-ellipsis">
Benchmarking
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
Benchmarking
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../overview/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../running_benchmarks/" class="md-nav__link">
<span class="md-ellipsis">
Running Benchmarks
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../attack_defense/" class="md-nav__link">
<span class="md-ellipsis">
Attack & Defense CTFs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../jeopardy_ctfs/" class="md-nav__link">
<span class="md-ellipsis">
Jeopardy CTFs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../cyber_ranges/" class="md-nav__link">
<span class="md-ellipsis">
Cyber Ranges
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
Knowledge Benchmarks
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Knowledge Benchmarks
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#available-benchmarks" class="md-nav__link">
<span class="md-ellipsis">
📊 Available Benchmarks
</span>
</a>
<nav class="md-nav" aria-label="📊 Available Benchmarks">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#seceval" class="md-nav__link">
<span class="md-ellipsis">
SecEval
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cybermetric" class="md-nav__link">
<span class="md-ellipsis">
CyberMetric
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#ctibench" class="md-nav__link">
<span class="md-ellipsis">
CTIBench
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#what-knowledge-benchmarks-measure" class="md-nav__link">
<span class="md-ellipsis">
🎯 What Knowledge Benchmarks Measure
</span>
</a>
<nav class="md-nav" aria-label="🎯 What Knowledge Benchmarks Measure">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#security-concept-understanding" class="md-nav__link">
<span class="md-ellipsis">
Security Concept Understanding
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#threat-intelligence" class="md-nav__link">
<span class="md-ellipsis">
Threat Intelligence
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#incident-response" class="md-nav__link">
<span class="md-ellipsis">
Incident Response
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#risk-assessment" class="md-nav__link">
<span class="md-ellipsis">
Risk Assessment
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#alias1-knowledge-performance" class="md-nav__link">
<span class="md-ellipsis">
🏆 alias1 Knowledge Performance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#running-knowledge-benchmarks" class="md-nav__link">
<span class="md-ellipsis">
🚀 Running Knowledge Benchmarks
</span>
</a>
<nav class="md-nav" aria-label="🚀 Running Knowledge Benchmarks">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#prerequisites" class="md-nav__link">
<span class="md-ellipsis">
Prerequisites
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cybermetric-evaluation" class="md-nav__link">
<span class="md-ellipsis">
CyberMetric Evaluation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#seceval-evaluation" class="md-nav__link">
<span class="md-ellipsis">
SecEval Evaluation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#ctibench-evaluation" class="md-nav__link">
<span class="md-ellipsis">
CTIBench Evaluation
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#output-structure" class="md-nav__link">
<span class="md-ellipsis">
📁 Output Structure
</span>
</a>
<nav class="md-nav" aria-label="📁 Output Structure">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#example-informationtxt" class="md-nav__link">
<span class="md-ellipsis">
Example information.txt
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#evaluation-metrics" class="md-nav__link">
<span class="md-ellipsis">
📊 Evaluation Metrics
</span>
</a>
<nav class="md-nav" aria-label="📊 Evaluation Metrics">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#accuracy" class="md-nav__link">
<span class="md-ellipsis">
Accuracy
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#category-performance" class="md-nav__link">
<span class="md-ellipsis">
Category Performance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#response-quality" class="md-nav__link">
<span class="md-ellipsis">
Response Quality
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#why-knowledge-benchmarks-matter" class="md-nav__link">
<span class="md-ellipsis">
🎓 Why Knowledge Benchmarks Matter
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#research-papers" class="md-nav__link">
<span class="md-ellipsis">
📚 Research Papers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#related-benchmarks" class="md-nav__link">
<span class="md-ellipsis">
🔗 Related Benchmarks
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#get-started" class="md-nav__link">
<span class="md-ellipsis">
🚀 Get Started
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../privacy_benchmarks/" class="md-nav__link">
<span class="md-ellipsis">
Privacy Benchmarks
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_5" >
<label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="">
<span class="md-ellipsis">
Guides
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_5">
<span class="md-nav__icon md-icon"></span>
Guides
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../running_agents/" class="md-nav__link">
<span class="md-ellipsis">
Running Agents
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../continue_mode/" class="md-nav__link">
<span class="md-ellipsis">
Continue Mode
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../results/" class="md-nav__link">
<span class="md-ellipsis">
Working with Results
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../streaming/" class="md-nav__link">
<span class="md-ellipsis">
Streaming
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tracing/" class="md-nav__link">
<span class="md-ellipsis">
Tracing & Debugging
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../context/" class="md-nav__link">
<span class="md-ellipsis">
Context Management
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../guardrails/" class="md-nav__link">
<span class="md-ellipsis">
Guardrails & Security
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../environment_variables/" class="md-nav__link">
<span class="md-ellipsis">
Environment Variables
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cai/getting-started/packet_capture_wsl/" class="md-nav__link">
<span class="md-ellipsis">
Packet Capture on WSL2
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_6" >
<label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="">
<span class="md-ellipsis">
Troubleshooting
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_6">
<span class="md-nav__icon md-icon"></span>
Troubleshooting
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../cai/troubleshooting/operator_feedback_reproduction/" class="md-nav__link">
<span class="md-ellipsis">
Operator Feedback Reproduction
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cai/troubleshooting/platform_limitations/" class="md-nav__link">
<span class="md-ellipsis">
Platform Limitations
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_7" >
<label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="">
<span class="md-ellipsis">
Case Studies
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_7">
<span class="md-nav__icon md-icon"></span>
Case Studies
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../cai/case-studies/operator-artifact-evidence/" class="md-nav__link">
<span class="md-ellipsis">
Operator Artifact Evidence
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_8" >
<label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="">
<span class="md-ellipsis">
Mobile UI (iOS)
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_8">
<span class="md-nav__icon md-icon"></span>
Mobile UI (iOS)
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../mui/mui_index/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../mui/getting_started/" class="md-nav__link">
<span class="md-ellipsis">
Getting Started
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../mui/user_interface/" class="md-nav__link">
<span class="md-ellipsis">
User Interface
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../mui/gestures_shortcuts/" class="md-nav__link">
<span class="md-ellipsis">
Gestures & Shortcuts
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../mui/chat_features/" class="md-nav__link">
<span class="md-ellipsis">
Chat Features
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_9" >
<label class="md-nav__link" for="__nav_9" id="__nav_9_label" tabindex="">
<span class="md-ellipsis">
Terminal UI (TUI) - Deprecated
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_9_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_9">
<span class="md-nav__icon md-icon"></span>
Terminal UI (TUI) - Deprecated
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../tui/tui_index/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tui/getting_started/" class="md-nav__link">
<span class="md-ellipsis">
Getting Started
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tui/user_interface/" class="md-nav__link">
<span class="md-ellipsis">
User Interface
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tui/terminals_management/" class="md-nav__link">
<span class="md-ellipsis">
Terminals Management
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tui/teams_and_parallel_execution/" class="md-nav__link">
<span class="md-ellipsis">
Teams & Parallel Execution
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tui/sidebar_features/" class="md-nav__link">
<span class="md-ellipsis">
Sidebar Features
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tui/keyboard_shortcuts/" class="md-nav__link">
<span class="md-ellipsis">
Keyboard Shortcuts
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tui/commands_reference/" class="md-nav__link">
<span class="md-ellipsis">
Commands Reference
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tui/advanced_features/" class="md-nav__link">
<span class="md-ellipsis">
Advanced Features
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../tui/troubleshooting/" class="md-nav__link">
<span class="md-ellipsis">
Troubleshooting
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10" >
<label class="md-nav__link" for="__nav_10" id="__nav_10_label" tabindex="">
<span class="md-ellipsis">
API Reference
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_10_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10">
<span class="md-nav__icon md-icon"></span>
API Reference
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10_1" >
<label class="md-nav__link" for="__nav_10_1" id="__nav_10_1_label" tabindex="0">
<span class="md-ellipsis">
Agents
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_10_1_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10_1">
<span class="md-nav__icon md-icon"></span>
Agents
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../ref/agent/" class="md-nav__link">
<span class="md-ellipsis">
Agent
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/run/" class="md-nav__link">
<span class="md-ellipsis">
Runner
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/tool/" class="md-nav__link">
<span class="md-ellipsis">
Tool
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/result/" class="md-nav__link">
<span class="md-ellipsis">
Result
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/stream_events/" class="md-nav__link">
<span class="md-ellipsis">
Stream Events
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/handoffs/" class="md-nav__link">
<span class="md-ellipsis">
Handoffs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/lifecycle/" class="md-nav__link">
<span class="md-ellipsis">
Lifecycle
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/items/" class="md-nav__link">
<span class="md-ellipsis">
Items
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/run_context/" class="md-nav__link">
<span class="md-ellipsis">
Run Context
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/usage/" class="md-nav__link">
<span class="md-ellipsis">
Usage
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/exceptions/" class="md-nav__link">
<span class="md-ellipsis">
Exceptions
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/guardrail/" class="md-nav__link">
<span class="md-ellipsis">
Guardrail
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/model_settings/" class="md-nav__link">
<span class="md-ellipsis">
Model Settings
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/agent_output/" class="md-nav__link">
<span class="md-ellipsis">
Agent Output
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/function_schema/" class="md-nav__link">
<span class="md-ellipsis">
Function Schema
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10_2" >
<label class="md-nav__link" for="__nav_10_2" id="__nav_10_2_label" tabindex="0">
<span class="md-ellipsis">
Models
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_10_2_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10_2">
<span class="md-nav__icon md-icon"></span>
Models
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../ref/models/interface/" class="md-nav__link">
<span class="md-ellipsis">
Interface
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/models/openai_chatcompletions/" class="md-nav__link">
<span class="md-ellipsis">
OpenAI Chat Completions
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/models/openai_responses/" class="md-nav__link">
<span class="md-ellipsis">
OpenAI Responses
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_10_3" >
<label class="md-nav__link" for="__nav_10_3" id="__nav_10_3_label" tabindex="0">
<span class="md-ellipsis">
Extensions
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="2" aria-labelledby="__nav_10_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_10_3">
<span class="md-nav__icon md-icon"></span>
Extensions
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../ref/extensions/handoff_filters/" class="md-nav__link">
<span class="md-ellipsis">
Handoff Filters
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../ref/extensions/handoff_prompt/" class="md-nav__link">
<span class="md-ellipsis">
Handoff Prompt
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_11" >
<label class="md-nav__link" for="__nav_11" id="__nav_11_label" tabindex="">
<span class="md-ellipsis">
Advanced
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_11_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_11">
<span class="md-nav__icon md-icon"></span>
Advanced
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../cai_development/" class="md-nav__link">
<span class="md-ellipsis">
Development
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_12" >
<label class="md-nav__link" for="__nav_12" id="__nav_12_label" tabindex="">
<span class="md-ellipsis">
Research
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_12_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_12">
<span class="md-nav__icon md-icon"></span>
Research
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../research/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_13" >
<label class="md-nav__link" for="__nav_13" id="__nav_13_label" tabindex="">
<span class="md-ellipsis">
Resources
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_13_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_13">
<span class="md-nav__icon md-icon"></span>
Resources
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../../cai_faq/" class="md-nav__link">
<span class="md-ellipsis">
FAQ
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cai_find_us/" class="md-nav__link">
<span class="md-ellipsis">
Find Us
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../../cai_citation_and_acknowledgments/" class="md-nav__link">
<span class="md-ellipsis">
Citation & Acknowledgments
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#available-benchmarks" class="md-nav__link">
<span class="md-ellipsis">
📊 Available Benchmarks
</span>
</a>
<nav class="md-nav" aria-label="📊 Available Benchmarks">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#seceval" class="md-nav__link">
<span class="md-ellipsis">
SecEval
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cybermetric" class="md-nav__link">
<span class="md-ellipsis">
CyberMetric
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#ctibench" class="md-nav__link">
<span class="md-ellipsis">
CTIBench
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#what-knowledge-benchmarks-measure" class="md-nav__link">
<span class="md-ellipsis">
🎯 What Knowledge Benchmarks Measure
</span>
</a>
<nav class="md-nav" aria-label="🎯 What Knowledge Benchmarks Measure">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#security-concept-understanding" class="md-nav__link">
<span class="md-ellipsis">
Security Concept Understanding
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#threat-intelligence" class="md-nav__link">
<span class="md-ellipsis">
Threat Intelligence
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#incident-response" class="md-nav__link">
<span class="md-ellipsis">
Incident Response
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#risk-assessment" class="md-nav__link">
<span class="md-ellipsis">
Risk Assessment
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#alias1-knowledge-performance" class="md-nav__link">
<span class="md-ellipsis">
🏆 alias1 Knowledge Performance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#running-knowledge-benchmarks" class="md-nav__link">
<span class="md-ellipsis">
🚀 Running Knowledge Benchmarks
</span>
</a>
<nav class="md-nav" aria-label="🚀 Running Knowledge Benchmarks">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#prerequisites" class="md-nav__link">
<span class="md-ellipsis">
Prerequisites
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#cybermetric-evaluation" class="md-nav__link">
<span class="md-ellipsis">
CyberMetric Evaluation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#seceval-evaluation" class="md-nav__link">
<span class="md-ellipsis">
SecEval Evaluation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#ctibench-evaluation" class="md-nav__link">
<span class="md-ellipsis">
CTIBench Evaluation
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#output-structure" class="md-nav__link">
<span class="md-ellipsis">
📁 Output Structure
</span>
</a>
<nav class="md-nav" aria-label="📁 Output Structure">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#example-informationtxt" class="md-nav__link">
<span class="md-ellipsis">
Example information.txt
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#evaluation-metrics" class="md-nav__link">
<span class="md-ellipsis">
📊 Evaluation Metrics
</span>
</a>
<nav class="md-nav" aria-label="📊 Evaluation Metrics">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#accuracy" class="md-nav__link">
<span class="md-ellipsis">
Accuracy
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#category-performance" class="md-nav__link">
<span class="md-ellipsis">
Category Performance
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#response-quality" class="md-nav__link">
<span class="md-ellipsis">
Response Quality
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#why-knowledge-benchmarks-matter" class="md-nav__link">
<span class="md-ellipsis">
🎓 Why Knowledge Benchmarks Matter
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#research-papers" class="md-nav__link">
<span class="md-ellipsis">
📚 Research Papers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#related-benchmarks" class="md-nav__link">
<span class="md-ellipsis">
🔗 Related Benchmarks
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#get-started" class="md-nav__link">
<span class="md-ellipsis">
🚀 Get Started
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="knowledge-benchmarks">Knowledge Benchmarks</h1>
<p>Knowledge benchmarks evaluate AI models' understanding of cybersecurity concepts, threat intelligence, vulnerability analysis, and security best practices through question-answering and knowledge extraction tasks.</p>
<hr />
<h2 id="available-benchmarks">📊 Available Benchmarks</h2>
<h3 id="seceval">SecEval</h3>
<p>Benchmark designed to evaluate LLMs on security-related tasks including phishing email analysis, vulnerability classification, and response generation.</p>
<ul>
<li><strong>Type</strong>: Multiple choice and open-ended questions</li>
<li><strong>Coverage</strong>: Phishing detection, malware analysis, vulnerability assessment, security policy</li>
<li><strong>Dataset</strong>: Real-world security scenarios</li>
<li><strong>Source</strong>: <a href="https://github.com/XuanwuAI/SecEval">SecEval Repository</a></li>
</ul>
<h3 id="cybermetric">CyberMetric</h3>
<p>Framework focusing on measuring AI performance in cybersecurity-specific question answering, knowledge extraction, and contextual understanding.</p>
<ul>
<li><strong>Type</strong>: Question-answering with contextual reasoning</li>
<li><strong>Coverage</strong>: Security concepts, best practices, incident response, threat modeling</li>
<li><strong>Emphasis</strong>: Domain knowledge and reasoning ability</li>
<li><strong>Source</strong>: <a href="https://github.com/CyberMetric">CyberMetric Repository</a></li>
</ul>
<h3 id="ctibench">CTIBench</h3>
<p>Benchmark focused on evaluating LLM capabilities in understanding and processing Cyber Threat Intelligence (CTI) information.</p>
<ul>
<li><strong>Type</strong>: Multiple choice questions and attribute extraction</li>
<li><strong>Coverage</strong>: Threat actor analysis, malware attribution, IOC extraction, MITRE ATT&amp;CK mapping</li>
<li><strong>Dataset</strong>: CTI-MCQ (multiple choice) and CTI-ATE (attribute extraction)</li>
<li><strong>Source</strong>: <a href="https://github.com/xashru/cti-bench">CTIBench Repository</a></li>
</ul>
<hr />
<h2 id="what-knowledge-benchmarks-measure">🎯 What Knowledge Benchmarks Measure</h2>
<h3 id="security-concept-understanding">Security Concept Understanding</h3>
<ul>
<li>Vulnerability types and classifications</li>
<li>Attack vectors and techniques</li>
<li>Defense mechanisms and controls</li>
<li>Security principles and best practices</li>
</ul>
<h3 id="threat-intelligence">Threat Intelligence</h3>
<ul>
<li>Threat actor capabilities and motivations</li>
<li>Malware families and characteristics</li>
<li>Indicators of Compromise (IOCs)</li>
<li>Tactics, Techniques, and Procedures (TTPs)</li>
</ul>
<h3 id="incident-response">Incident Response</h3>
<ul>
<li>Incident detection and classification</li>
<li>Response procedures and priorities</li>
<li>Forensic analysis techniques</li>
<li>Recovery and remediation strategies</li>
</ul>
<h3 id="risk-assessment">Risk Assessment</h3>
<ul>
<li>Threat modeling methodologies</li>
<li>Vulnerability scoring (CVSS)</li>
<li>Risk prioritization frameworks</li>
<li>Security architecture evaluation</li>
</ul>
<hr />
<h2 id="alias1-knowledge-performance">🏆 alias1 Knowledge Performance</h2>
<div class="admonition success">
<p class="admonition-title">Superior Knowledge Capabilities</p>
<p><strong><code>alias1</code> demonstrates exceptional performance</strong> on cybersecurity knowledge benchmarks:</p>
<ul>
<li>🥇 <strong>Highest accuracy</strong> across all three major knowledge benchmarks</li>
<li>🥇 <strong>Contextual understanding</strong> - Correctly interprets complex security scenarios</li>
<li>🥇 <strong>Zero refusals</strong> - Provides comprehensive answers for all security questions</li>
<li>🥇 <strong>Technical depth</strong> - Detailed explanations with practical examples</li>
</ul>
<p><strong>General-purpose models show</strong>:
- ❌ Lower accuracy on specialized security concepts
- ❌ Oversimplified or generic responses
- ❌ Refusals on sensitive security topics
- ❌ Missing contextual nuances in CTI analysis</p>
</div>
<p><strong><a href="../../cai_pro/">Get alias1 with CAI PRO →</a></strong></p>
<hr />
<h2 id="running-knowledge-benchmarks">🚀 Running Knowledge Benchmarks</h2>
<h3 id="prerequisites">Prerequisites</h3>
<div class="language-bash highlight"><pre><span></span><code><span id="__span-0-1"><span class="c1"># Install dependencies</span>
</span><span id="__span-0-2">pip<span class="w"> </span>install<span class="w"> </span>cvss
</span><span id="__span-0-3">
</span><span id="__span-0-4"><span class="c1"># Configure API keys in .env file</span>
</span><span id="__span-0-5"><span class="nv">ALIAS_API_KEY</span><span class="o">=</span><span class="s2">&quot;sk-your-caipro-key&quot;</span><span class="w"> </span><span class="c1"># For alias1</span>
</span><span id="__span-0-6"><span class="nv">OPENAI_API_KEY</span><span class="o">=</span><span class="s2">&quot;sk-...&quot;</span><span class="w"> </span><span class="c1"># For OpenAI models</span>
</span><span id="__span-0-7"><span class="nv">ANTHROPIC_API_KEY</span><span class="o">=</span><span class="s2">&quot;sk-ant-...&quot;</span><span class="w"> </span><span class="c1"># For Anthropic models</span>
</span><span id="__span-0-8"><span class="nv">OLLAMA_API_BASE</span><span class="o">=</span><span class="s2">&quot;http://localhost:11434/v1&quot;</span><span class="w"> </span><span class="c1"># For local models</span>
</span></code></pre></div>
<h3 id="cybermetric-evaluation">CyberMetric Evaluation</h3>
<div class="language-bash highlight"><pre><span></span><code><span id="__span-1-1"><span class="c1"># Using alias1 (recommended)</span>
</span><span id="__span-1-2">python<span class="w"> </span>benchmarks/eval.py<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-3"><span class="w"> </span>--model<span class="w"> </span>alias1<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-4"><span class="w"> </span>--dataset_file<span class="w"> </span>benchmarks/cybermetric/CyberMetric-2-v1.json<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-5"><span class="w"> </span>--eval<span class="w"> </span>cybermetric<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-6"><span class="w"> </span>--backend<span class="w"> </span><span class="nb">alias</span>
</span><span id="__span-1-7">
</span><span id="__span-1-8"><span class="c1"># Using Ollama with Qwen</span>
</span><span id="__span-1-9">python<span class="w"> </span>benchmarks/eval.py<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-10"><span class="w"> </span>--model<span class="w"> </span>ollama/qwen2.5:14b<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-11"><span class="w"> </span>--dataset_file<span class="w"> </span>benchmarks/cybermetric/CyberMetric-2-v1.json<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-12"><span class="w"> </span>--eval<span class="w"> </span>cybermetric<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-13"><span class="w"> </span>--backend<span class="w"> </span>ollama
</span><span id="__span-1-14">
</span><span id="__span-1-15"><span class="c1"># Using OpenAI GPT-4o</span>
</span><span id="__span-1-16">python<span class="w"> </span>benchmarks/eval.py<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-17"><span class="w"> </span>--model<span class="w"> </span>gpt-4o-mini<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-18"><span class="w"> </span>--dataset_file<span class="w"> </span>benchmarks/cybermetric/CyberMetric-2-v1.json<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-19"><span class="w"> </span>--eval<span class="w"> </span>cybermetric<span class="w"> </span><span class="se">\</span>
</span><span id="__span-1-20"><span class="w"> </span>--backend<span class="w"> </span>openai
</span></code></pre></div>
<h3 id="seceval-evaluation">SecEval Evaluation</h3>
<div class="language-bash highlight"><pre><span></span><code><span id="__span-2-1"><span class="c1"># Using alias1</span>
</span><span id="__span-2-2">python<span class="w"> </span>benchmarks/eval.py<span class="w"> </span><span class="se">\</span>
</span><span id="__span-2-3"><span class="w"> </span>--model<span class="w"> </span>alias1<span class="w"> </span><span class="se">\</span>
</span><span id="__span-2-4"><span class="w"> </span>--dataset_file<span class="w"> </span>benchmarks/seceval/eval/datasets/questions-2.json<span class="w"> </span><span class="se">\</span>
</span><span id="__span-2-5"><span class="w"> </span>--eval<span class="w"> </span>seceval<span class="w"> </span><span class="se">\</span>
</span><span id="__span-2-6"><span class="w"> </span>--backend<span class="w"> </span><span class="nb">alias</span>
</span><span id="__span-2-7">
</span><span id="__span-2-8"><span class="c1"># Using Anthropic Claude</span>
</span><span id="__span-2-9">python<span class="w"> </span>benchmarks/eval.py<span class="w"> </span><span class="se">\</span>
</span><span id="__span-2-10"><span class="w"> </span>--model<span class="w"> </span>claude-3-7-sonnet-20250219<span class="w"> </span><span class="se">\</span>
</span><span id="__span-2-11"><span class="w"> </span>--dataset_file<span class="w"> </span>benchmarks/seceval/eval/datasets/questions-2.json<span class="w"> </span><span class="se">\</span>
</span><span id="__span-2-12"><span class="w"> </span>--eval<span class="w"> </span>seceval<span class="w"> </span><span class="se">\</span>
</span><span id="__span-2-13"><span class="w"> </span>--backend<span class="w"> </span>anthropic
</span></code></pre></div>
<h3 id="ctibench-evaluation">CTIBench Evaluation</h3>
<div class="language-bash highlight"><pre><span></span><code><span id="__span-3-1"><span class="c1"># Multiple choice questions</span>
</span><span id="__span-3-2">python<span class="w"> </span>benchmarks/eval.py<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-3"><span class="w"> </span>--model<span class="w"> </span>alias1<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-4"><span class="w"> </span>--dataset_file<span class="w"> </span>benchmarks/cti_bench/data/cti-mcq1.tsv<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-5"><span class="w"> </span>--eval<span class="w"> </span>cti_bench<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-6"><span class="w"> </span>--backend<span class="w"> </span><span class="nb">alias</span>
</span><span id="__span-3-7">
</span><span id="__span-3-8"><span class="c1"># Attribute extraction tasks</span>
</span><span id="__span-3-9">python<span class="w"> </span>benchmarks/eval.py<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-10"><span class="w"> </span>--model<span class="w"> </span>alias1<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-11"><span class="w"> </span>--dataset_file<span class="w"> </span>benchmarks/cti_bench/data/cti-ate2.tsv<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-12"><span class="w"> </span>--eval<span class="w"> </span>cti_bench<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-13"><span class="w"> </span>--backend<span class="w"> </span><span class="nb">alias</span>
</span><span id="__span-3-14">
</span><span id="__span-3-15"><span class="c1"># Using OpenRouter</span>
</span><span id="__span-3-16">python<span class="w"> </span>benchmarks/eval.py<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-17"><span class="w"> </span>--model<span class="w"> </span>qwen/qwen3-32b:free<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-18"><span class="w"> </span>--dataset_file<span class="w"> </span>benchmarks/cti_bench/data/cti-mcq1.tsv<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-19"><span class="w"> </span>--eval<span class="w"> </span>cti_bench<span class="w"> </span><span class="se">\</span>
</span><span id="__span-3-20"><span class="w"> </span>--backend<span class="w"> </span>openrouter
</span></code></pre></div>
<hr />
<h2 id="output-structure">📁 Output Structure</h2>
<p>Results are saved to structured directories:</p>
<div class="language-text highlight"><pre><span></span><code><span id="__span-4-1">outputs/
</span><span id="__span-4-2">└── cybermetric/ (or seceval, cti_bench)
</span><span id="__span-4-3"> └── alias1_20250115_abc123/
</span><span id="__span-4-4"> ├── answers.json # Complete test with responses
</span><span id="__span-4-5"> └── information.txt # Performance metrics
</span></code></pre></div>
<h3 id="example-informationtxt">Example information.txt</h3>
<div class="language-text highlight"><pre><span></span><code><span id="__span-5-1">Model: alias1
</span><span id="__span-5-2">Benchmark: cybermetric
</span><span id="__span-5-3">Accuracy: 92.5%
</span><span id="__span-5-4">Total Questions: 100
</span><span id="__span-5-5">Correct: 92
</span><span id="__span-5-6">Incorrect: 8
</span><span id="__span-5-7">Runtime: 145 seconds
</span><span id="__span-5-8">Date: 2025-01-15
</span><span id="__span-5-9">Backend: alias
</span></code></pre></div>
<hr />
<h2 id="evaluation-metrics">📊 Evaluation Metrics</h2>
<h3 id="accuracy">Accuracy</h3>
<p>Percentage of correctly answered questions:
<div class="language-text highlight"><pre><span></span><code><span id="__span-6-1">Accuracy = (Correct Answers / Total Questions) × 100%
</span></code></pre></div></p>
<h3 id="category-performance">Category Performance</h3>
<p>Breakdown by question category:
- Vulnerability analysis: 95%
- Threat intelligence: 90%
- Incident response: 88%
- Security architecture: 92%</p>
<h3 id="response-quality">Response Quality</h3>
<p>Qualitative assessment of answer quality:
- Correctness
- Completeness
- Technical depth
- Practical applicability</p>
<hr />
<h2 id="why-knowledge-benchmarks-matter">🎓 Why Knowledge Benchmarks Matter</h2>
<p>Knowledge benchmarks are essential for evaluating cybersecurity AI because:</p>
<ol>
<li><strong>Foundation Skills</strong> - Tests understanding of core security concepts</li>
<li><strong>Decision Making</strong> - Evaluates ability to make informed security judgments</li>
<li><strong>Contextual Reasoning</strong> - Assesses comprehension beyond memorization</li>
<li><strong>Practical Application</strong> - Measures ability to apply knowledge to scenarios</li>
<li><strong>Domain Expertise</strong> - Validates specialized cybersecurity understanding</li>
</ol>
<p>Unlike hands-on CTF challenges, knowledge benchmarks assess the <strong>theoretical foundation</strong> that enables effective security analysis and decision-making.</p>
<hr />
<h2 id="research-papers">📚 Research Papers</h2>
<ul>
<li>
<p>📊 <a href="https://arxiv.org/pdf/2510.24317"><strong>CAIBench: Cybersecurity AI Benchmark</strong></a> (2025)
Includes knowledge benchmark evaluation methodology.</p>
</li>
<li>
<p>🚀 <a href="https://arxiv.org/pdf/2504.06017"><strong>Cybersecurity AI (CAI) Framework</strong></a> (2025)
Demonstrates knowledge-driven security operations.</p>
</li>
</ul>
<p><strong><a href="https://aliasrobotics.com/research-security.php#papers">View all research →</a></strong></p>
<hr />
<h2 id="related-benchmarks">🔗 Related Benchmarks</h2>
<ul>
<li><strong><a href="../privacy_benchmarks/">Privacy Benchmarks</a></strong> - PII handling evaluation</li>
<li><strong><a href="../jeopardy_ctfs/">Jeopardy CTFs</a></strong> - Practical skill assessment</li>
<li><strong><a href="../running_benchmarks/">Running Benchmarks</a></strong> - Setup and usage guide</li>
</ul>
<hr />
<h2 id="get-started">🚀 Get Started</h2>
<p>Knowledge benchmarks are <strong>freely available</strong> to all CAI users.</p>
<p><strong><a href="../../cai_installation/">Download CAI and start benchmarking →</a></strong></p>
<p>For best performance, <strong><a href="../../cai_pro/">upgrade to CAI PRO for alias1 →</a></strong></p>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "../..", "features": ["content.code.copy", "content.code.select", "navigation.path", "navigation.sections", "navigation.expand", "content.code.annotate"], "search": "../../assets/javascripts/workers/search.f8cc74c7.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="../../assets/javascripts/bundle.c8b220af.min.js"></script>
</body>
</html>