A public chatbot receives requests for secrets and harmful content.
Control both sides of the model boundary.
Choose two appropriate controls.
Inspect input for prohibited content and injection indicators, and inspect output for secrets, harmful content, and policy violations.
Detailed explanation
A model can still generate unsafe content.
Input checks alone cannot guarantee safe output.
Logs need minimization, access control, and retention rules.
Dangerous requests can be rejected or isolated before generation.
Check official documentation
Compare the following points with the official documentation.
Amazon Bedrock Guardrails公式資料とAIF-C01 Domain 5.1の入出力保護を確認する。
Official references
What to confirm
入力だけでなく出力も検査する多層防御を説明できる。
Key points
- Input
- Output
- Defense in depth
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
Guardrail
A policy-based control that detects, blocks, or transforms unsafe or prohibited content.
Input validation
Checking request data for allowed type, size, format, content, and authorization before processing.