AI Runtime Security
SCM
Table of Contents
Expand All
|
Collapse All
AI Runtime Security Docs
-
- AI Models on Public Clouds Support
-
- Deploy AI Runtime Security: Network Intercept in GCP
- Deploy AI Runtime Security: Network Intercept in Azure
- Deploy AI Runtime Security: Network Intercept in AWS
- Configure Strata Cloud Manager to Secure VM Workloads and Kubernetes Clusters
- Harvest IP-Tags from Public and Hybrid Kubernetes Clusters to Enforce Security Policy Rules
- AI Runtime Security for Private Clouds
- Manually Deploy and Bootstrap AI Runtime Security: Network Intercept
SCM
Create an AI security profile to enable AI application protection, AI data
protection, and AI model protections to your security policy rules.
Where Can I Use This? | What Do I Need? |
---|---|
|
- Log in to Strata Cloud Manager.
- Navigate to Manage → Configuration → NGFW and Prisma Access → Security Services → AI Security.
- Select the Configuration Scope as Global or limit it to your AI security profile.
- Select AI Security → Add Profile.
- Enter a Name and a Description.
- Add Model Group for customized protections. See Create Model Groups for Customized Protections.For example, a model group with URL categorization and prompt injection alert settings is attached to the following security profile for a target AI model. You can attach a security policy as a zone or a DAG:
- For zone-based security, follow the use case on how to Create Traffic Objects for Zone-Based Security using specific clusters to monitor the ingress and east-west traffic. Attach this zone to a security policy rule to enforce policies on the AI traffic sourced from this zone and the traffic objects within this zone.
- For protecting the source AI applications, use Dynamic Address Groups in Policy and reference these DAGs in the security policy rule.
- In the Advanced Settings, under Latency:
- 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
- Create.