365Architect

Threat Taxonomy

This section catalogues the primary attack vectors targeting AI/ML systems. Each page maps to MITRE ATLAS techniques and cites the relevant OWASP LLM Top 10, NIST AI 600-1, and EU AI Act provisions.

In This Section

Threat MITRE ATLAS OWASP LLM Top 10 NIST AI 600-1
Prompt Injection TA0012.003 LLM01 §2.9, §2.8
Jailbreaks TA0012.003 LLM01 §2.9, §2.3
Adversarial Attacks TA0012.001 LLM01, LLM04 §2.1, §2.2
Data Poisoning TA0012.002 LLM03 §2.3
Model Extraction TA0004.002, TA0013 LLM10 §2.10
Supply-Chain Attacks TA0002, TA0006 LLM05 §2.12
Agent Hijacking TA0005, TA0008 LLM07, LLM08 §2.7, §2.12

Threat Modelling Approach

  1. Identify your ML assets — models, training data, feature store, pipeline, endpoints
  2. Select relevant ATLAS tactics — based on deployment model (cloud API, edge, embedded)
  3. Map techniques to your attack surface — e.g., public API → prioritise ML Model Access (TA0004) and ML Attack Staging (TA0012)
  4. Define mitigations per technique — using NIST AI 600-1 actions, OWASP LLM controls, ISO 42001 Annex A controls
  5. Track coverage — maintain a matrix: Asset × ATLAS Tactic × Technique × Mitigation × Residual Risk

Cross-References

Share

Keyboard Shortcuts

⌘ K
Open search
/
Focus search
?
Show shortcuts
b
Toggle bookmark
Alt+←
Previous page
Alt+→
Next page
Esc
Close overlay