Configure check items

Procedure

1. Log on to the AI Guardrails console.

2. In the left-side navigation pane, choose Protection Configuration > Model Protection.

   The detection item configuration list displays the available Services:

   • AI Input Content Safety Detection (Pro edition) (query_security_check_pro): detects text content submitted to the large model.

   • AI Output Content Safety Detection (Pro edition) (response_security_check_pro): detects text content generated by the large model.

   • AIGC Input Image Security Detection (img_query_security_check): detects image content submitted by users.

   • AIGC Image Security Detection (img_response_security_check): detects image content generated by the large model.

3. In the Actions column of the target Service, click Management to go to the Service management page.

4. In the Protection Dimension area, view the detection capabilities supported by the current Service. Each protection dimension is displayed as a card with a toggle to enable or disable the feature.

   Text-based Services support the following protection dimensions:

   • Content compliance: detects pornographic, violent, political, and other undesirable content. Enabled by default.

   • Sensitive content detection: detects personal information or enterprise sensitive data that may be leaked.

   • Prompt injection detection: detects malicious prompts designed to bypass the safety limits of large models.

   • Malicious URL (public preview): scans content from large models for malicious links.

   • Model Hallucination (public preview): detects false or inaccurate information generated by large models.

   Note

   Enabling Sensitive content detection or Prompt injection detection incurs separate charges. For details, see Activation and billing.

5. Vocabulary settings: In the detection item configuration list, configure a vocabulary for a text-based Service to add blocklist or allowlist entries. For details, see Vocabulary management.

Configuration management

On the Service management page, click Configuration Management on a Protection Dimension card to configure the detection toggles and detailed rules for each risk tag under that dimension.

Take AI Input Content Safety Detection (Pro edition) (query_security_check_pro) as an example. In the detection item configuration list, click Management in the Actions column.

1. In the Protection Dimension area, click Configuration Management on the target dimension card (for example, Content compliance).

2. Select the detection type to adjust, click Edit to enter edit mode, and modify the detection status.

   Note

   Difference between baseline rules and independent rules update mechanism

   • Using baseline rules directly: Detection capabilities automatically sync to the latest version as official updates are released. No manual adjustment is required.

   • Independent rules created by copying a Service: Updates to baseline rules do NOT automatically sync to copied independent rules. The independent rules retain their original configuration. To use the latest strategy on an independent rule, you must manually edit and synchronize the configuration. When you copy a Service, the new Service's configuration (including billing method, configurable items, and custom vocabulary settings) is the same as the source Service.

3. Click Save. Changes take effect in approximately 2 to 5 minutes.

   Important

   Policy adjustment delay notice

   Due to the delay in policy propagation, testing immediately after a configuration change may produce inconsistent results or false positives (for example, phone numbers being incorrectly blocked). Wait for a period of time after modifying a policy before re-sending requests to verify that the latest policy has taken effect.

FAQ