تست نفوذ هوش مصنوعی و امنیت سیستم‌های مبتنی بر AI

عنوان دوره : Maven – AI Red Teaming & AI Security Masterclass

سطح : مبتدی

زمان کل دوره : 11 ساعت و 42 دقیقه

تعداد فايل ها : 14

سال آموزش : 2026

فایل تمرینی : دارد: HTML (28)، PDF (4)، PPTX (4)

مربی دوره : Sander Schulhoff

نرم افزار : –

زیرنویس انگلیسی : ندارد

Maven – AI Red Teaming & AI Security Masterclass

Your AI Systems Are Vulnerable… Learn how to Secure Them!

The #1 AI Red Teaming Course. Taught by HackAPrompt, creators of the 1st AI Red Teaming Competition

Prompt injection attacks are the #1 security vulnerability in AI systems. HackAPrompt’s research helped OpenAI increase their model’s resistance to prompt injections by up to 46%. Our recent research with OpenAI, Anthropic, and Google DeepMind found humans outperform automated AI Red Teaming.

That’s why companies need trained AI Red Teamers, and why we built this course.

Using HackAPrompt, you’ll gain hands-on experience identifying prompt injections, jailbreaks, and adversarial attacks – learning to break AI systems and secure them.

Plus, access recorded hacking sessions with top AI Red Teamers who share their favorite techniques, including:

Pliny the Prompter – World’s most renowned AI jailbreaker

Johann Rehberger – Built Microsoft Azure Red Teams

Richard Lundeen – Microsoft AI Red Team Lead

Valen T. – 1st in Anthropic’s Red Teaming competition

& more!

The training prepares you for our AIRTP+ certification exam, which has certified 100’s from Microsoft, Google, Capital One, IBM, ServiceNow, and Walmart.

For enterprise training: team@learnprompting.org
What you’ll learn

Learn how to uncover AI vulnerabilities, run real attacks, and apply defenses that secure systems in production.

Understand How AI Systems Fail

Learn how prompt injections, jailbreaks, and adversarial inputs actually succeed

Study real model behavior to identify weak points in prompts, context, and integrations

Recognize where traditional security assumptions break down in AI applications

Build Core Red Teaming Skills

Run hands-on attacks in a controlled environment to expose real vulnerabilities

Trace how manipulations happen by analyzing system outputs and behavior

Use red teaming workflows to validate risks and stress-test AI features

Design Practical and Effective AI Defenses

Apply validation, filtering, and safety controls that strengthen system behavior

Test defenses under realistic conditions to confirm they prevent exploitation

Build repeatable evaluation routines that surface failures early

Secure AI Systems Through Real-World Projects

Investigate live systems for vulnerabilities and test exploitation paths

Repair insecure flows and measure the impact of your fixes

Complete projects that prepare you for the AIRTP+ exam through practical, exam-aligned work