AI Threat Frameworks
- OWASP MAESTRO – Multi-agent environment threat modeling
- MITRE ATLAS – Adversarial Threat Landscape for AI Systems
- MITRE ATT&CK for AI – Extending ATT&CK for AI-specific adversary tactics
AI Governance and Compliance
- NIST AI Risk Management Framework (AI RMF) – Risk-based AI governance
- ISO/IEC 42001:2023 – AI Management Systems standard
- EU AI Act Overview – Risk-tiered regulatory framework for AI in Europe
Red Teaming and Offensive AI
- Google Secure AI Framework (SAIF) – Secure AI deployment best practices
- Anthropic’s AI Red Teaming Approaches – Red teaming strategies for AI models
- OpenAI System Card – Risk disclosure and testing practices for GPT models
- Stanford Center for Research on Foundation Models (CRFM) – Safety and red teaming studies
Offensive Security (General)
- MITRE ATT&CK Framework – Adversary tactics, techniques, and procedures (TTPs)
- OWASP Top Ten – Common web application vulnerabilities
ZioSec Perspectives (Coming Soon)
- Whitepapers on offensive AI testing
- Case studies from enterprise AI deployments
- Research insights on emerging GenAI threats