The AWS AI Security Framework: Securing AI with the right controls, at the right layers, at the right phases

### Executive summary This AWS whitepaper introduces the AWS AI Security Framework to help organizations secure AI workloads from prototype to production by mapping controls to three use cases (answering, connecting to data, acting/agents), three defensive layers (infrastructure, identity & data, AI application), and three deployment phases (foundational, enhanced, advanced), and by recommending AWS services and operational practices (e.g., Amazon Bedrock Guardrails, IAM, KMS, GuardDuty) for defense-in-depth, governance, and incident preparedness.