← AWS Certified Generative AI Developer - Professional
AWS · objective · 20% of the exam
AI Safety, Security, and Governance — AWS Certified Generative AI Developer - Professional
The official AWS documentation our AI Safety, Security, and Governance practice questions are cited to. Review the primary sources, then practise.
Official references for this objective
-
Amazon Web Services — Responsible Ai Lens.Pdf
Security: Protecting data and models from exfiltration and adversarial inputs. • Safety: Blocking harmful system output and misuse. • Veracity: Achieving factually
-
Amazon Web Services — AI lifecycle risk management: ISO/IEC 42001:2023 for AI governance | AWS Security Blog
DREAD (damage potential, reproducibility, exploitability, affected users, and discoverability) is a framework that can assess severity of individual threats
-
Amazon Web Services — Securing Generative AI: The Generative AI Security Scoping Matrix
You build a customer support chatbot that integrates your own data using Retrieval-Augmented Generation (RAG) and leverages the Anthropic Claude foundation model through Amazon Bedrock
-
Amazon Web Services — Build safe generative AI applications like a Pro: Best Practices with Amazon Bedrock Guardrails | Artificial Intelligence
If the initial configuration produces too many false positives: Lower the filter strength to MEDIUM Re-evaluate with sample traffic Continue adjusting as needed, moving to
-
Amazon Web Services — Fairness, model explainability and bias detection with SageMaker Clarify - Amazon SageMaker AI
SageMaker Clarify needs model predictions to compute post-training bias metrics and feature attributions
-
Amazon Web Services — Responsible use - Amazon Nova
customers must evaluate the potential risks of their use case and implement appropriate human oversight, testing, and other use-case specific safeguards to mitigate such risks