Guide
AI Adversarial Test Reference
This annex provides the adversarial test case library, red team methodology, and tooling guidance supporting the AI and Agentic Development Security Standard §§21 to 23. Test cases must be maintained quarterly per ADTEST-SEC-01.
- Type
- Guide
- Version
- 1.3.19
- Date
- 2026-10-27
- Owner
- Chief Information Security Officer
- Approving authority
- Governance Library Maintainer
- Classification
- Public
- Confidentiality
- Public
- Category
- AI Governance
- Review frequency
- 6 to 12 months and upon material AI framework or regulatory change
- Licence
- CC BY-SA 4.0
Read the full text on GitHub (opens in a new tab)
Outline
- B1. Adversarial test categories (required for all systems in scope)
- B2. Red team methodology
- B3. Test suite maintenance
- B4. TikiTribe integration
- B5. External references
Related documents
- AI and Agentic Development Security Standardai
- AI Security and Risk Standardai
- AI Testing, Validation and Documentation Standardai
- Adversarial Evaluation Suite Development Guidelineai
- AI Evaluation Procedureai
- AI Security Technical Implementation Guideai
Next
All Documents