Generated by Code IQ · v1.0

garak
Knowledge Tutorial

garak serves as an automated vulnerability scanner for Large Language Models (LLMs), functioning similarly to a red team or penetration tester. It orchestrates a workflow where Probes generate malicious prompts to attack a target Generator, Buffs obfuscate these attacks, Detectors analyze the model's outputs for failures, and Evaluators grade the overall security posture.

7
Chapters
-
Subsystems
Rabbit Holes
▶ Start Reading ⎇ View on GitHub
System Architecture

How the pieces fit

garak is organized as connected concepts and components. Start broad, then drill down chapter by chapter.

⚙️
Generators (Model Interfaces)
Generators (Model Interfaces)
⚙️
Probes (Attack Vectors)
Probes (Attack Vectors)
⚙️
Detectors (Vulnerability Scanners)
Detectors (Vulnerability Scanners)
⚙️
Harness (Orchestrator)
Harness (Orchestrator)
⚙️
Attempt (Interaction Context)
Attempt (Interaction Context)
⚙️
Evaluators (Scorekeepers)
Evaluators (Scorekeepers)
⚙️
Buffs (Fuzzers/Perturbations)
Buffs (Fuzzers/Perturbations)
garak — bash
open tutorial
◆ Scanning numbered chapters
◆ Building navigation and Mermaid diagrams
◆ Generating chapter and subsystem pages
✓ 7 chapter pages built
✓ Theme toggle enabled
Repository Overview

Intro and Architecture Diagram

garak serves as an automated vulnerability scanner for Large Language Models (LLMs), functioning similarly to a red team or penetration tester. It orchestrates a workflow where Probes generate malicious prompts to attack a target Generator, Buffs obfuscate these attacks, Detectors analyze the model's outputs for failures, and Evaluators grade the overall security posture.

Source Repository: https://github.com/NVIDIA/garak

flowchart TD A0["Probes (Attack Vectors)"] A1["Generators (Model Interfaces)"] A2["Detectors (Vulnerability Scanners)"] A3["Harness (Orchestrator)"] A4["Attempt (Interaction Context)"] A5["Evaluators (Scorekeepers)"] A6["Buffs (Fuzzers/Perturbations)"] A3 -->|"Executes"| A0 A0 -->|"Creates"| A4 A0 -->|"Applies"| A6 A6 -->|"Modifies prompt in"| A4 A0 -->|"Queries"| A1 A3 -->|"Runs"| A2 A2 -->|"Analyzes output in"| A4 A3 -->|"Triggers evaluation"| A5 A5 -->|"Grades results in"| A4
Tutorial Chapters

All 7 chapters

Follow sequentially or jump to any topic. Start with Generators (Model Interfaces).

About This Project

Generated by Code IQ

This tutorial was automatically generated by Code IQ and rendered with the shared tutorial site builder. It can be produced for any repository tutorial folder that follows the numbered markdown chapter layout.

View Code IQ ↗
python build_site.py '/home/runner/work/Code-IQ/Code-IQ/output/garak'

// → 7 chapters
// → source: NVIDIA/garak