5.1Standard
Personal documents are embedded for retrieval.
Limit leakage from vectors.
Choose two designs.
× Incorrect
Minimize, mask, and authorize before indexing, separating source and vector access and managing retention, encryption, audit, and deletion for derivatives.
Detailed explanation
IncorrectA vector cannot be personal data because it is not text
It can reveal or infer sensitive information.
IncorrectDelete sources but retain vectors and caches forever
Derived copies remain.
CorrectCheck purpose, minimization, masking, and authorization before indexing and separate source and vector access
Exposure is reduced.
CorrectManage retention, deletion, encryption, and audit for vectors, sources, metadata, and backups
Derived copies are covered.
Check official documentation
Compare the following points with the official documentation.
AWS公式AIF-C01 Domain 3.1・5.1の埋め込み、派生データ、プライバシーを確認する。
Official references
What to confirm
ベクトルを原文とは別の派生データとして扱い、削除とアクセスを一貫管理できる。
Key points
- Embedding
- Derived data
- Reidentification
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
Embedding privacy
The risk that a vector representation reveals or enables inference about source information.
Derived-data deletion
Removing outputs that were produced from a source when that source must be removed.
Question IDAWS-AIF-513
EnvironmentAWS公式AIF-C01試験ガイドとAWS公式ドキュメントの確認
Last technical review2026-08-20
Report an error or rights issue