add biometric abuse monitoring

Author: Jinyu Li

articles/ai-services/computer-vision/concept-liveness-abuse-monitoring.md

@@ -23,7 +23,7 @@ Details on how data is handled can be found on the [Data, Privacy, and Security]
 
 [!INCLUDE [liveness-sdk-gate](./includes/liveness-sdk-gate.md)]
 
-## Components of abuse monitoring
+## Components of abuse monitoring in Face API V1.2 and earlier
 
 There are several components to Face liveness abuse monitoring:
 - **Session management**: Your backend application system creates liveness detection sessions on behalf of your end-users. The Face service issues authorization tokens for a particular session, and each is valid for a limited number of API calls. When the end-user encounters a failure during liveness detection, a new token is requested. This allows the backend application to assess the risk of allowing more liveness retries. An excessive number of retries may indicate a brute force adversarial attempt to bypass the liveness detection system.
@@ -32,6 +32,10 @@ There are several components to Face liveness abuse monitoring:
 - **Human review and decision**: When the correlation identifiers are flagged through abuse pattern capture as described above, no further sessions can be created for those identifiers. You should allow authorized employees to assess the traffic patterns and either confirm or override the determination based on predefined guidelines and policies. If human review concludes that an override is needed, you should generate a new temporary correlation GUID for the individual in order to generate more sessions.
 - **Notification and action**: When a threshold of abusive behavior has been confirmed based on the preceding steps, the customer should be informed of the determination by email. Except in cases of severe or recurring abuse, customers typically are given an opportunity to explain or remediate—and implement mechanisms to prevent the recurrence of—the abusive behavior. Failure to address the behavior, or recurring or severe abuse, may result in the suspension or termination of your Limited Access eligibility for Azure AI Face resources and/or capabilities.
 
+## Additional components of abuse monitoring in v1.3 
+
+-	Version 1.3 liveness detection introduces an extra component to improve abuse monitoring. This feature monitors matching facial templates across temporary correlation identifiers and will flag potential abuse in liveness detection results when similar facial templates are repeatedly used with different temporary correlation identifiers. Incorrectly setting up a temporary correlation identifier may also cause this feature to flag abuse. You can turn off this feature if you think it is not applicable to your use case.
+
 ## Related content
 
 - [Learn more about understanding and mitigating risks associated with identity management](/azure/security/fundamentals/identity-management-overview)