Google Cloud training

Model Armor: Securing AI Deployments

This course explains how to use Model Armor to protect AI applications, specifically large language models (LLMs).The curriculum covers Model Armor's architecture and its role in mitigating threats like malicious URLs, prompt injection, jailbreaking, sensitive data leaks, and improper output handling.Practical skills include defining floor settings, configuring templates, and enabling various detection types. You'll also explore sample audit logs to find details about flagged violations.

  • Duration: 2h 30m
  • Languages: English, German
  • Level: Introductory
  • Group size: Up to 50

What you'll learn

  • Explain the purpose of Model Armor in a company's security portfolio.
  • Define the protections applied to all interactions with the LLM.
  • Identify the OWASP LLM vulnerabilities that Model Armor addresses.
  • Set up the Model Armor API and find flagged violations in Security Command Center (SCC).
  • Identify how the system intercepts and manages prompts and responses to ensure safety.

Prerequisites

  • Working knowledge of APIs.
  • Working knowledge of Google Cloud CLI.
  • Working knowledge of cloud security foundational principles.
  • Familiarity with the Google Cloud console.

Course outline

Course overview
  • What's in it for me?
Model Armor overview
  • About Model Armor
  • LLM security risks
Customize Model Armor
  • About customization
  • Floor settings
  • Guard rails and confidence levels
  • Templates
Use Model Armor
  • About setup
  • API setup
  • Flagged violations
Put it all together
  • Prompts and responses
  • Application code
Course conclusion
  • What did I learn?

Related courses

Not sure which course fits?

Book a 30-minute call. We'll look at where your team is, what they need to be able to do, and put together either a specific course date or a tailored learning plan.