Only an internal application should call an inference API.
Prevent unauthenticated direct calls.
Choose two controls.
Separate caller authentication and authorization, and combine TLS, short-lived tokens, rate limits, audit logs, and input-size limits.
Detailed explanation
Identity and allowed action are controlled.
Identity and allowed action are controlled.
Communication, abuse, and traceability are protected.
Communication, abuse, and traceability are protected.
Internal compromise remains possible.
Internal compromise remains possible.
It can leak easily.
It can leak easily.
Try it yourself
An example you can run in a temporary verification environment.
AWS公式AIF-C01 Domain 5.1の推論エンドポイント、IAM、認証、監査を確認する。Expected result
推論APIへの呼出し主体・権限・通信・濫用を多層で制御できる。Key points
- Authentication
- Authorization
- Short-lived token
Notes
- Environment: AWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
- Command output formatting can vary slightly by distribution or tool version.
- Run the example in a temporary directory or process when possible.
Foundation review
Read the scope first
Check whether the command acts on the current shell, a new process, an existing process, or a file.
Verify the observable result
Use the supplied command and compare the output with the expected result.