Model Armor: Securing AI Deployments (MODARM)

 

Course Overview

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.

Who should attend

  • Security engineers
  • AI/ML developers
  • Cloud architects

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 Objectives

  • Explain the purpose of Model Armor in a company’s security portfolio.
  • Define the protections that Model Armor applies to all interactions with the LLM.
  • Set up the Model Armor API and find flagged violations.
  • Identify how Model Armor manages prompts and responses.

Outline: Model Armor: Securing AI Deployments (MODARM)

Module 1 - Course overview

Topics

  • What’s in it for me?

Objectives

  • Recall the course learning objectives.

Module 2 - Model Armor overview

Topics

  • About Model Armor
  • LLM security risks

Objectives

  • Explain the purpose of Model Armor in a company’s security portfolio.
  • Identify the subset of top 10 OWASP LLM vulnerabilities that Model Armor addresses.
  • Identify Model Armor key concepts and architecture.
  • Map Model Armor features to the security risks they mitigate.

Activities

  • Knowledge check
  • Quiz

Module 3 - Customize Model Armor

Topics

  • About customization
  • Floor settings
  • Guard rails and confidence levels
  • Templates

Objectives

  • Define the protections that Model Armor applies to all interactions with the LLM.
  • Describe floor settings and explain how they work.
  • Explain the purpose of a template and how it works with the API.
  • Configure the four types of detections in the template

Activities

  • Knowledge check
  • Quiz

Module 4 - Use Model Armor

Topics

  • About setup
  • API setup
  • Flagged violations

Objectives

  • Set up the Model Armor API and find flagged violations.
  • Explain the prerequisites that are required to work with the API.
  • Describe how to enable the API.
  • Set up logging in the template, explore types of audit logs, and find them in SCC.
  • Explain how to find floor setting violations in SCC and resolve them.

Activities

  • Quiz

Module 5 - Put it all together

Topics

  • Prompts and responses
  • Application code

Objectives Identify how Model Armor intercepts and manages prompts and responses. ELO:

  • Explain how Model Armor reviews prompts and reports findings based on content safety flags.
  • Explain how Model Armor reviews LLM responses and updates them according to template settings.
  • Execute various commands for sanitizing user prompts against different security features.

Activities

  • Quiz

Module 6 - Course conclusion

Topics

  • What did I learn?

Objectives

  • Summarize the course learning objectives.

Prices & Delivery methods

Online Training

Duration
2.5 hours

Price
  • CAD 820
Classroom Training

Duration
2.5 hours

Price
  • Canada: CAD 820

Schedule

Currently there are no training dates scheduled for this course.