0
1.0.0
Zurich Patch 4, Yokohama Patch 11
Integration
Cisco AI Defense integration can be used to import AI security exposures such as model vulnerabilities and model validation findings (automated red teaming alerts) into AI Security Exposure Management and automate workflows for remediation.
Cisco AI Defense is a security platform that can identify security weaknesses in AI models and other AI assets.
This integration with AI Security Exposure Management retrieves the following types of records from Cisco AI Defense:
- AI model vulnerabilities: Vulnerabilities identified in open-source AI models (e.g., malicious code) scanned by Cisco.
- AI model validation findings: Results of automated red teaming or model validation tests run by Cisco to identify model behavior risks.
Initial Innovation Lab release.
Required roles:
The following Now Platform roles are required for this integration:
- sn_vul_cisco_ai_df.admin - Full access to manage integrations and read the AI security data
- sn_vul_cisco_ai_df.read - Read-only access to view AI security data and integrations
Required Now Platform applications:
- AI Security Exposure Management 1.0.0
- Vulnerability Response Integration Framework (sn_vul_int_fw)
- AI Security (sn_sec_ai)
- AI Discovery (sn_ai_disc)
- A Cisco AI Defense Account:
-
- Active Cisco AI Defense subscription
-
- API access credentials (Tenant API Key)
Supported family releases:
Yokohama Patch 11 (YP11)
Zurich Patch 4 (ZP4)