Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
AI Red Teaming & LLM Hacking - A Practical Guide with Labs
Rating: 4.4 out of 5(33 ratings)
3,173 students

AI Red Teaming & LLM Hacking - A Practical Guide with Labs

Hands-on course on LLM security: learn prompt injection, jailbreaks, adversarial attacks, and defensive controls
Created byHassan Shafiq
Last updated 7/2026
English
English [Auto],

What you'll learn

  • Build a Pro-Level AI Hacking Lab: Get the official Microsoft AI Red Teaming Playground running locally using Docker and Azure OpenAI
  • nstall Uncensored Models: Go beyond the labs and learn to install and run uncensored, local LLMs for unrestricted adversarial testing.
  • Master Direct Prompt Injection (Challenges 1 & 7): Learn to "jailbreak" an AI to exfiltrate sensitive files, including the "Grandma Exploit"
  • Steal the AI's "Brain" (Challenges 2 & 8): Master Metaprompt Extraction by using deceptive logic puzzles and encoding tricks to make the AI leak its own secret
  • Execute the Crescendo Attack (Challenges 3, 4 & 5): Learn the most powerful multi-turn attack.
  • Bypass Active Guardrails : Apply advanced Crescendo techniques to defeat an AI that is actively trying to block you, learning how to adapt your attack
  • Poison the Well (Challenges 6, 11 & 12): Master Indirect Prompt Injection, the stealthiest attack.
  • Think Like an Attacker: Understand why these attacks work, how they map to the OWASP Top 10 for LLMs

Course content

6 sections • 18 lectures • 1h 25m total length

  • Introduction to the Course1:12

    Learn to think like an attacker to test AI security through direct and indirect prompt injection, multi-turn attacks, and red-teaming labs, including uncensored local models.

Requirements

  • A computer that can run Docker Desktop (Windows, Mac, or Linux).
  • An active Microsoft Azure subscription. (A new account with free credits is sufficient).
  • No prior red teaming or coding experience is necessary. We will walk through everything, step-by-step.

Description

“This course contains the use of artificial intelligence.”

AI Red Teaming is no longer a niche skill—it is one of the most in-demand specialties in all of cybersecurity. As companies race to integrate Generative AI into their products, they are exposing themselves to a new class of vulnerabilities. The #1 risk, according to OWASP, is Prompt Injection —and the only way to defend against it is to learn how to do it yourself.

This is the most practical, hands-on, and comprehensive guide to AI hacking available. We will be using the official Microsoft AI Red Teaming Playground —the same set of labs taught by Microsoft's own AI Red Team at Black Hat USA.

This is 100% hands-on. I will guide you, step-by-step, through practical challenges. You will not just see the solution—you will see the process. I will show you the prompts that fail and explain why they fail. Then, I will show you the prompts that succeed and break down the psychology and technical tricks that make them work.

This course is built on the official "AI Red Teaming 101" Microsoft Learn series , but goes even further. We'll start by building our lab from scratch, then add bonus modules on installing your own uncensored local AI models so you can practice these attacks without any filters.

What We Will Master:

  1. Lab Setup : A complete, manual walkthrough of setting up the Microsoft AI Red Teaming Labs with Docker and a free Microsoft Azure account.

  2. Direct Prompt Injection: Learn single-turn jailbreaks to exfiltrate credentials. We'll cover everything from simple instruction overrides to advanced social engineering and emotional manipulation prompts.

  3. Metaprompt Extraction : Trick the AI into leaking its own "secret sauce." You'll learn to use creative, deceptive prompts to steal the system prompt.

  4. The Crescendo Attack: Master the sophisticated multi-turn attack. We'll start innocent conversations and gradually "steer" the AI into bypassing its safety alignment to generate instructions for weapons, toxins, and profanity.

  5. Bypassing Guardrails: We'll level up our attack to defeat an AI with active defenses, learning how to "backtrack" and rephrase our prompts when the model resists.

  6. Indirect Prompt Injection: Execute the most dangerous attack. You'll learn to "poison" an external webpage with hidden instructions (in HTML comments and CSS) that hijack the AI when a normal user asks it to summarize the page.

  7. Install Uncensored LLM ( AI model): Want more from your LLM. Learn to install uncensored LLM on your local PC.

By the end of this course, you won't just know what AI red teaming is. You will have a practical, repeatable skill set.

Who this course is for:

  • Cybersecurity Professionals: Red Teamers, Penetration Testers, and Security Analysts who need to add AI hacking to their toolkit.
  • AI/ML Engineers & Developers: Learn to think like an attacker so you can build secure AI applications and defend against prompt injection.
  • Product Managers: Understand the real-world risks of the AI products you are building.
  • Compliance & Governance Officers: See firsthand how AI systems can be manipulated to violate safety and data privacy policies.
  • Tech-Savvy Beginners: Anyone interested in AI security. If you can use ChatGPT, you can take this course. No prior coding is required.

Report abuse