Secure Generative AI with Amazon Bedrock

Course details

While the promise of generative AI is boundless, it comes hand-in-hand with unique security considerations. In this course, AWS-certified software programmer and DevOps advocate Dipali Kulshrestha explores generative AI as a tool to revolutionize customer experiences, innovate uncharted applications, and elevate organizational productivity, while also discussing the corresponding security considerations. Learn about Amazon Bedrock and the very convenient way it provides to simplify generative AI development, with foundation models from Amazon and leading AI startups. Explore the architectures, data flows, and security-related aspects of model fine-tuning, as well as the prompting and inference phases. Plus, find out how Amazon Bedrock uses AWS security services and capabilities, such as AWS KMS, AWS CloudTrail, and AWS Identity and Access Management (IAM).

Concepts

0. Introduction

01 - Security concerns in generative AI

1. Introduction to Generative AI

02 - Importance of security in generative AI development
03 - Addressing ethical challenges in generative AI development
04 - Ethical best practices for generative AI
05 - Introduction to generative AI models and techniques
06 - Overview of AWS services used in generative AI development

2. Securing Generative AI Models Using Amazon Bedrock

07 - Introduction to Amazon Bedrock
08 - Amazon Bedrock features and its workflow
09 - Foundation models (FMs) supported by Amazon Bedrock
10 - Knowledge base for Amazon Bedrock
11 - Agents for Amazon Bedrock
12 - Datasets and vector embeddings
13 - Architecture patterns with Bedrock
14 - Amazon Bedrock Dashboard overview (Demo)
15 - Integrating FMs into your code with Amazon Bedrock (Demo)

3. Network Security for Generative AI Applications

16 - Client connectivity with Bedrock
17 - Guardrails for Amazon Bedrock

4. Security of the GenAI Model

18 - Data privacy and localization
19 - Data security - Data in transit
20 - Data security - Data at rest

5. Security in the GenAI Model

21 - Use and misuse of GenAI models
22 - GenAI security scoping

6. Securing Data Flows

23 - Single-tenancy vs. multi-tenancy
24 - Multi-tenancy inference
25 - Single-tenancy inference
26 - Model fine-tuning

7. Secure Deployment of Generative AI Models

27 - Deploy GenAI models with SageMaker JumpStart
28 - Deploy GenAI models on Amazon EKS

8. Compliance and Governance in Amazon Bedrock-Based Generative AI

29 - IAM
30 - Implementing auditing, logging, and compliance mechanisms
31 - Infrastructure security
32 - Cross-service confused deputy prevention
33 - Configuration and vulnerability analysis in Amazon Bedrock
34 - Configurable security controls

9. Emerging Trends in Generative AI Security with Amazon Bedrock

35 - Monitor Amazon Bedrock
36 - Quotas for Amazon Bedrock

Conclusion

37 - Learning more about generative AI in AWS