AWS Security: Securing Generative AI on AWS

This course was developed by members of AWS Technical Field Communities (TFC), an AWS community of technical experts. The content is intended to complement our standard training curriculum and augment your AWS learning journey.

This course is for Security and AI/ML technical users who need to know about securing generative AI on AWS.

You will learn how about the AWS Gen AI Security Scoping Matrix to help categorize and secure AI implementations. We will discuss the MITRE ATLAS framework and OWASPs Top 10 threats to Gen AI.

We will learn about comprehensive security strategies across governance, legal, and risk controls.

• Course level:

  Intermediate

• Duration:

  120 minutes

Activities

This course includes knowledge checks and a Bedrock technical demo video.

Course objectives

In this course, you will learn:

• Understand and apply the Generative AI Security Scoping Matrix to categorize and secure different AI implementations.
• Implement comprehensive security strategies across governance, legal, risk, controls, and resilience for various AI scopes.
• Navigate key AI security frameworks like OWASP Top 10 for LLMs and MITRE Atlas.
• Develop practical skills to secure generative AI workloads on AWS, from consumer applications to self-trained models.

Intended audience

• Architects
• Cloud Operators
• Data Engineers
• Data Scientists
• Developers
• DevOps Engineers
• Infrastructure Engineers
• Security Engineers

Recommended Skills

We recommend that attendees of this course have completed the following training:

• AWS Security Fundamentals
• Introduction to Generative AI - Art of the Possible

Course outline

• Module 1:

  Introduction to Generative AI Security

• Module 2:

  Generative AI Security Frameworks

• Module 3:

  Introducing the Generative AI Security Scoping Matrix

• Module 4:

  Securing Consumer AI Applications (Scope 1)

• Module 5:

  Securing Enterprise AI Applications (Scope 2)

• Module 6:

  Securing Pre-trained AI Models (Scope 3)

• Module 7:

  Securing Fine-tuned AI Models (Scope 4)

• Module 8:

  Securing Self-trained AI Models (Scope 5)

• Module 9:

  Generative AI security in practice & conclusion

Keywords

• Generative AI
• Gen AI
• Artificial Intelligence
• Security