Projects

AI Security Wiki

Most teams securing AI are rebuilding the same controls from scratch. I built the AI Security Wiki so you don't have to.

A free, vendor-neutral framework for security leaders, architects and GRC professionals who are securing AI systems in real environments. Free to use and modify under CC BY-SA 4.0.

Test cases for evaluating AI security products in a proof of concept

629

Control objectives, each citing OWASP, MITRE ATLAS, NIST AI RMF and ISO/IEC 42001

44

Regional regulatory sections, from the GCC and EU to India and Brazil

12

Fill-in templates, from an EU AI Act classification form to a DPDP processing record

51

Also Inside

• A 13-risk AI risk register with direct risk-to-control mapping
• Domain-specific standards for Browser AI, Coding Assistants, Custom LLM Applications and Agentic AI
• Sector overlays for financial services, insurance, health and government
• A Foundations paper on the difference between AI security and security of AI

Regions covered: GCC, EU, UK, US, India, Singapore, Japan, South Korea, China, Canada, Australia and Brazil. The regional legal content is compiled from secondary sources, with every claim tagged by how it was sourced. It is a starting point for verification, not legal advice.