AI Defense Inspection API

In today's rapidly evolving technological landscape, artificial intelligence (AI) offers transformative potential for enterprises. However, the integration and deployment of AI applications introduce unique security challenges that traditional cybersecurity measures may not fully address. Recognizing this, Cisco has introduced AI Defense, an end-to-end security solution designed to empower organizations to confidently develop, deploy, and manage AI applications.

AI Defense Runtime protection

AI Defense Runtime protection allows you to secure production AI applications with guardrails that block adversarial attacks and harmful responses in real time. AI Defense Runtime protection can be enforced using the AI Defense Inspection API, using an AI Gateway, or using Multicloud Defense. All of these approaches are explained in Runtime in the AI Defense documentation.

API-based policy enforcement

By using the AI Defense Inspection API, you can build runtime protection into your AI applications in the form of Inspection API calls. This allows you, the AI application developer, to specify how your AI application will handle violations detected in AI Defense.

API-based policy enforcement relies on other components of AI Defense:

  • Applications and policies are managed in the UI as explained in Runtime
  • The separate AI Defense Management API allows your CI/CD workflows to manage your applications and policies as explained in the AI Defense Management API documentation (Customer login required.)

Policies and rules

Regardless of enforcement approach, AI Defense Runtime protection relies on AI runtime rules, policies, and threat taxonomies. AI Defense Runtime protection and the AI Defense Inspection API enforce your policies and rules to ensure that only safe and permissible content is shared to and from AI applications. Rules are managed in the Policies section of AI Defense, and enforcement actions are reported in the AI Events screen when a policy is enforced, or in the API response when you enforce specific rules, rather than a policy.

What can you do with the AI Defense Inspection API?

  1. Prevent data leaks – Enforce security policies to stop sensitive data exposure.
  2. Secure AI applications – Protect AI applications and their data from threats.
  3. Inspect AI-generated content – Analyze chat messages and HTTP traffic for risks.

Track API version changes

See the API Changelog.