Your question is Defend ML Training from Data Poisoning. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
How do you secure machine learning training pipelines against data poisoning attacks at Amazon?
Explain a practical AWS design covering data provenance, access control, validation, isolation, monitoring, and incident response. Address both malicious dataset modification and compromised pipeline components, including how you verify that each control works.