Securing ML and AI Workloads

Least privilege for models and data, VPC isolation and KMS, audit trails with CloudTrail and Config, vulnerability scanning in CI/CD, Bedrock API keys versus IAM, and Guardrails.

Content current as of 2026-10.

Lessons

  1. Least privilege for ML artifacts
  2. VPCs, KMS, and Secrets Manager
  3. CloudTrail, Config, Inspector, CodeGuru
  4. Bedrock Guardrails and responsible AI safeguards

Sources