Hands-on course on LLM security: learn prompt injection, jailbreaks, adversarial attacks, and defensive controls
Sub Category
- Operations
{inAds}
Objectives
- 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
Pre Requisites
- 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.
FAQ
- Q. How long do I have access to the course materials?
- A. You can view and review the lecture materials indefinitely, like an on-demand channel.
- Q. Can I take my courses with me wherever I go?
- A. Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don't have an internet connection, some instructors also let their students download course lectures. That's up to the instructor though, so make sure you get on their good side!
{inAds}
Coupon Code(s)