GuardRail: Model Identity Protection

Model Identity Protection is WitnessAI's Jailbreak and Prompt Injection Guardrail. The purpose of this Guardrail is to protect Internal Models, or Models that are exposed by the business to the outside.

When these activities are detected, it provides the option to Allow, Warn, or Block the prompts with a customizable message.

WitnessAI Policies enable organizations to control, restrict, and protect the use of AI Models and Applications. Based on user activities, policies can block prompts, route usage to preferred AI Models or Applications, warn users, and maintain compliance with security and usage policies.

Click on the Guardrails tab (1).

Underneath the Guardrails tab, click on the Guardrail you’d like to configure (2).

Click the toggle to enable the Guardrail (3).

Underneath the Model Identity Protection title, choose the Model from the drop-down list (4).

Enter the prompt to send to the Model in the System Prompt section. (5)

If desired, click the Enable Response Protection toggle to enable (6).

Choose from “Allowlist” and “Blocklist” (7).

Add a Message under the list (8).

Enter a Behavior and Choose an Action (9, 10, 11).