The Cisco AI Defense application is a third-party integration supported by AI Security Exposure Management to import AI Defense scan results and model validation data for AI and machine learning models.
Cisco AI Defense is a security and governance platform that helps organizations discover, assess, and manage risks associated with AI and machine-learning models by providing visibility into AI usage, performing security and model validation scans, and monitoring for policy and compliance issues.
This integration with AI Security Exposure Management retrieves the following types of data from Cisco AI Defense:
- AI Security Scans - Detects vulnerabilities in AI model files, such as malicious code in serialized models with dangerous patterns.
- Model Validation Results - Tests performed on AI models against various attack scenarios to identify weaknesses that include prompts, responses, and threat signatures.
All imported data is stored in your CMDB in Now Platform AI Security tables for tracking, remediation, and reporting with automated workflows.
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)