Prisma AIRS
Get Familiar with AI Red Teaming Dashboard
Table of Contents
Get Familiar with AI Red Teaming Dashboard
Learn how to access the AI Red Teaming Dashboard.
| Where Can I Use This? | What Do I Need? |
|---|---|
|
|
The Red Teaming Dashboard allows you to launch AI apps
securely by rapidly testing AI apps against hundreds of real-world attacks. Use it
to deliver actionable insights for risk mitigation model selection and AI
defense.
To launch the Red Teaming Dashboard:
- Start with creating a deployment profile.Log in to Strata Cloud Manager (SCM).Navigate to .
![]()
The Red Teaming Dashboard contains information about your configuration, and is the starting point for configuring elements of your Red Teaming implementation. It contains the following areas:- Total Targets Added—Represents the total number of target endpoints of the AI system scanned for vulnerabilities.
- Targets Scanned—Represents the total number of targets scanned; one complete assessment of an AI system using Red Teaming is considered as a scan. A scan is carried out by sending attack payloads to an AI system in the form of attack prompts.
- Total Scans—Indicates the total scans
performed.Select View Details for additional information about Total Targets Added and Total Scans.
- Overview provides a graphical representation of
the results of your Red Teaming functionality. It includes areas for:
- Apps—AI powered systems designed for specific tasks or objectives.
- Agents—Specific application subtype where AI models are in charge of the control flow.
- Models—First party or third party models with a defined endpoint for simulation.
- Asset Risk Profile—Risk profile (high/medium/low) distribution of all AI assets (models, applications, agent) scanned with the AI Red Teaming tool.
Use the Strata Cloud Manager side bar navigation to access AI Red Teaming configuration options:![]()
Each of these configuration options are described in detail.
