AI Safety, Security, and Governance III
Explore methods to implement systematic fairness evaluations and enforce ethical AI policies in generative AI systems. Understand how to use AWS solutions such as SageMaker Clarify, Bedrock Guardrails, and automated bias detection to maintain secure and responsible AI deployments.
We'll cover the following...
We'll cover the following...
Question 48
A company is testing a GenAI-powered resume screening system to ensure it does not disadvantage candidates based on gender or ethnicity. The company wants a systematic, repeatable, and defensible fairness evaluation.
Which approaches should the company use? (Select any two options.)
A. Use SageMaker Clarify to detect bias across protected attributes.
B. Use Amazon ...