Integrate AI Guard

Procedure

1. Configure the AI Guard settings.
   1. Type a Name for the settings.
   2. Select a security level from the following:
      • Cautious
      • Moderate
      • Aggressive

      Note Trend Micro recommends selecting Moderate.

   3. Use the toggles to determine which content types AI Guard scans for:
      • Scan for harmful content
      • Scan for sensitive information
      • Scan for prompt attacks
   4. You can click Copy settings code to test the AI Guard settings in your environment.
2. Click Apply to save the settings.
3. Create an API key for AI Guard.
   1. Go to Administration → API Keys.
   2. Click Add API Key to create a new API key.
   3. Specify a name, user role, and expiration time for the API key.

      Important When adding the API key, you must select a Role with permission to run scans in AI Scanner. If your organization does not have an existing user role with the necessary permissions, create a custom role or contact your administrator.

      For more information, see API Keys.
   4. Click Add.
   5. Copy and retain the API key.
4. Integrate AI Guard with your application.
   Refer to the following code snippet for the integration.

   import os
   import requests
   
   # Get your Trend Vision One API key from environment variable
   api_key = os.environ.get("V1_API_KEY")
   if not api_key:
       raise ValueError("Missing V1_API_KEY environment variable")
   
   # Configure headers
   headers = {
       "Authorization": f"Bearer {api_key}",
       "Content-Type": "application/json"
   }
   
   # Prepare the payload for AI security scanning
   payload = {
       "guard": "your_prompt_or_response_here"
   }
   
   
   url = "https://<BASE_V1_URL>/beta/aiSecurity/guard?detailedResponse=false"
   
   # Make the API request
   response = requests.post(
       url,
       headers=headers,
       json=payload
   )
   
   # Check response status
   if response.status_code == 200:
       result = response.json()
       print("Scan completed successfully")
   else:
       print(f"Error: {response.status_code} - {response.text}")

   Note Trend Micro recommends storing your API key for AI Guard under the name $V1_API_KEY. Set the following as the base URL in the API request: <https://api.{region}.xdr.trendmicro.com/beta/aiSecurity> Unless your Trend Vision One account region is the US (the default region), replace {region} with the applicable region code in the base URL: eu jp au in sg mea

   For more information, see the AI Guard API reference.