Home / AWS Certified AI Practitioner (AIF-C01) / 5 Practice / AWS-AIF-430
Customer emails are sent to a summarization model.
Do not expose unnecessary personal data.
Choose two controls.
Hint 1: Focus on the requirement Remove unnecessary personal data before inference and protect the mapping that could restore original values.
Hint 2: Key terms Review minimization and masking.
Data minimizationLimiting collection and use to data necessary for a stated purpose.
MaskingReplacing sensitive values with a representation that hides the original.
TokenizationSubstituting a sensitive value with a reversible or controlled token.
Re-identification keyA protected mapping that can link a token back to an original identity. × Incorrect Minimize input and mask or tokenize unnecessary personal data, separating originals, replacement maps, logs, and restoration rights.
Detailed explanation A Incorrect Sending all personal data always maximizes quality
It violates purpose and minimization.
B Correct Detect and mask or tokenize names and contacts not needed for the purpose
Input exposure is reduced.
C Incorrect Make the replacement map publicly reversible
The secret is exposed.
D Correct Separate original data and replacement maps and control retention, logs, and restoration
Reidentification is controlled.
Check official documentation Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 5.1の個人情報、データ最小化、マスキングを確認する。
Official references Official documentation 1 Official documentation 2 What to confirm 個人情報を必要最小限にし、復元情報とモデル入力のアクセスを分離できる。
Key points 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 Compare the definition with the AIF-C01 objective and the service documentation before applying it. Keep the concept separate from a particular answer choice or implementation step. Foundation review Data minimization Limiting collection and use to data necessary for a stated purpose.
Masking Replacing sensitive values with a representation that hides the original.
Path & Pass is an independent learning site and is not affiliated with any certification body. Questions are original practice content based on published objectives.