A generative application receives customer free text.
Protect personal and confidential information in input, logs, and output.
Choose two controls.
Classify, mask, reject, or allow-list input data and apply retention, access, detection, and deletion controls to logs and output.
Detailed explanation
Models can reproduce sensitive input unintentionally.
Exposure and purpose limitation grow.
Unneeded sensitive data is kept out of the model request.
Non-input paths are included in data protection.
Check official documentation
Compare the following points with the official documentation.
AWS公式Amazon Bedrock Guardrails、ログ保護、AIF-C01 Domain 5.1を確認する。
Official references
What to confirm
入力、ログ、出力を一つのデータライフサイクルとして保護できる。
Key points
- Data classification
- Masking
- Log protection
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 classification
Assigning data categories such as public, internal, personal, or confidential to guide protection.
Data masking
Replacing or hiding sensitive values while retaining enough structure for an approved purpose.