: Objects > Security Profiles > AI Security
Focus
Focus

Objects > Security Profiles > AI Security

Table of Contents

Objects > Security Profiles > AI Security

You can attach an AI security profile to a security profile to detect threats in your cloud resources.
An AI security profile helps you configure specific security settings for:
  • AI application protection with URL categorization.
  • AI model protection against threats such as prompt injections.
  • AI data protection against sensitive data leakage to and from AI models.
The following table describes the AI Security Profile settings:
FieldDescription
NameEnter a unique name for the AI security profile.
DescriptionEnter a description for the AI security profile.
Model Groups (tab):
Add a model group for customized protections on the AI model, AI application, and AI data.
Select Add to add a new model group:
  • Name: Enter a name for the model group.
  • Target Models: Click Add.
    Select a cloud provider and the AI models supported by the cloud provider.
  • Access Control: Set the Access Control as Allow or Block for the model group.
  • ​​Configure the following Protection Settings for the Request and Response traffic:
    The Request has the protection settings for AI model protection, AI application protection, and AI data protection. The Response has protections for only AI application protection and AI data protection.
RequestResponse
AI Model Protection
  • Enable Prompt injection detection and set it to Alert or Block.
N/A
AI Application Protection
  • Set the default URL security behavior to Allow, Alert, or Block.
    You can override the default behavior for each custom URL setting.
  • In URL Security Exceptions, set actions for custom URL categories.
AI Application Protection
  • Set the default URL security behavior to Allow, Alert, or Block.
    You can override the default behavior for each custom URL setting.
  • In URL Security Exceptions, set actions for custom URL categories.
AI Data Protection
  • Data Rule: Select the predefined or custom DLP rules.
AI Data Protection
  • Data Rule: Select the predefined or custom DLP rules.
  • Database Security: Detect and regulate the AI model output interacting with an application database.
Set an Allow, Alert, or Block action on the database queries (Create, Read, Update, and Delete) to prevent unauthorized access.
Advanced (tab):
  • Max Inline Latency: Set the maximum allowed latency for inline threat detection. The latency range is between 1-300 seconds.
  • Inline Timeout Action: Specify the action to take if inline threat detection exceeds the Max Inline Latency:
    • Allow
    • Alert (Report threats asynchronously)
    • Block