# AI Security Wiki

A versioned map of the Databricks AI Security Framework, compiled for people and agents. [Start an audit](https://mathborgess.github.io/ai-security-wiki/wiki/methodology.md) · [Português](https://mathborgess.github.io/ai-security-wiki/README.pt-BR.md) · [MCP](https://mathborgess.github.io/ai-security-wiki/docs/mcp.md) · [Sources](https://mathborgess.github.io/ai-security-wiki/wiki/sources.md)

Snapshot 2026-10-22, DASF 3.0: **97 risks, 73 controls, 13 components, 7 deployment patterns**. These counts describe the compendium, not all possible AI security knowledge.

## Navigate by architecture

- [1. Raw data](https://mathborgess.github.io/ai-security-wiki/wiki/components/1.md) — 11 risks
- [2. Data preparation](https://mathborgess.github.io/ai-security-wiki/wiki/components/2.md) — 4 risks
- [3. Datasets](https://mathborgess.github.io/ai-security-wiki/wiki/components/3.md) — 3 risks
- [4. Data catalog governance](https://mathborgess.github.io/ai-security-wiki/wiki/components/4.md) — 2 risks
- [5. Machine learning algorithms](https://mathborgess.github.io/ai-security-wiki/wiki/components/5.md) — 4 risks
- [6. Evaluation](https://mathborgess.github.io/ai-security-wiki/wiki/components/6.md) — 3 risks
- [7. Machine learning models](https://mathborgess.github.io/ai-security-wiki/wiki/components/7.md) — 4 risks
- [8. Model management](https://mathborgess.github.io/ai-security-wiki/wiki/components/8.md) — 4 risks
- [9. Serving: inference requests](https://mathborgess.github.io/ai-security-wiki/wiki/components/9.md) — 13 risks
- [10. Serving: inference responses](https://mathborgess.github.io/ai-security-wiki/wiki/components/10.md) — 6 risks
- [11. Operations](https://mathborgess.github.io/ai-security-wiki/wiki/components/11.md) — 1 risks
- [12. Data and AI platform](https://mathborgess.github.io/ai-security-wiki/wiki/components/12.md) — 7 risks
- [13. Agentic AI](https://mathborgess.github.io/ai-security-wiki/wiki/components/13.md) — 35 risks

## Select every deployment pattern

- [Predictive ML Models](https://mathborgess.github.io/ai-security-wiki/wiki/deployments/predictive-ml.md)
- [RAG - LLMs](https://mathborgess.github.io/ai-security-wiki/wiki/deployments/rag.md)
- [Fine-tuned LLMs](https://mathborgess.github.io/ai-security-wiki/wiki/deployments/fine-tuned-llm.md)
- [Pre-trained LLMs](https://mathborgess.github.io/ai-security-wiki/wiki/deployments/pre-trained-llm.md)
- [Foundational LLMs](https://mathborgess.github.io/ai-security-wiki/wiki/deployments/foundation-llm.md)
- [External Models](https://mathborgess.github.io/ai-security-wiki/wiki/deployments/external-model.md)
- [Agentic AI](https://mathborgess.github.io/ai-security-wiki/wiki/deployments/agentic-ai.md)

## Investigation and learning

- [Audit method](https://mathborgess.github.io/ai-security-wiki/wiki/methodology.md)
- [Security research: PentAGI, Cloudflare and Red Blue Field](https://mathborgess.github.io/ai-security-wiki/wiki/research/index.md)
- [Evidence-driven audit playbook](https://mathborgess.github.io/ai-security-wiki/guides/evidence-driven-audit.md)
- [Jason Haddix study: recon, tools and reports](https://mathborgess.github.io/ai-security-wiki/wiki/research/jason-haddix.md)
- [Map attack surface skill](https://mathborgess.github.io/ai-security-wiki/skills/map-attack-surface/SKILL.md)
- [Pocket cybersecurity specialist](https://mathborgess.github.io/ai-security-wiki/skills/ask-cyber-specialist/SKILL.md)
- [Jason Haddix posts and media](https://mathborgess.github.io/ai-security-wiki/wiki/research/jason-haddix-media.md)
- [Evaluate models, guardrails and applications with spikee](https://mathborgess.github.io/ai-security-wiki/wiki/research/spikee-evaluation.md)
- [Agent and MCP trust boundaries](https://mathborgess.github.io/ai-security-wiki/wiki/agent-security.md)
- [Glossary](https://mathborgess.github.io/ai-security-wiki/wiki/glossary.md)
- [Finding template](https://mathborgess.github.io/ai-security-wiki/wiki/templates/finding.md)
- [Source-listed third-party tools](https://mathborgess.github.io/ai-security-wiki/wiki/toolkit.md)
- [Source inconsistencies](https://mathborgess.github.io/ai-security-wiki/wiki/source-issues.md)
- [All controls](https://mathborgess.github.io/ai-security-wiki/wiki/controls.md)
- [Source and update policy](https://mathborgess.github.io/ai-security-wiki/wiki/sources.md)
- [Change log](https://mathborgess.github.io/ai-security-wiki/wiki/log.md)