Create exception patterns to override AI Runtime Security detection verdicts for
specific content, and attach them to AI Security Profiles.
| Where Can I Use This? | What Do I Need? |
- Prisma AI Runtime Security
|
- Prisma AIRS AI Runtime Security license
- AI Runtime Security deployed (network intercept or API
intercept)
|
Exception patterns let you override AI Runtime Security detection verdicts for specific
content without reporting an incorrect verdict first. Benign patterns override
false positives. Malicious patterns override false negatives. The AI Security
Profile then applies its configured enforcement actions (such as Allow, Alert, or Block)
based on the resulting verdict. You can create patterns independently in
, test them in the sandbox before saving, and attach them to
one or more AI Security Profiles.