Source directory 12 documents
The primary sources behind the catalogue
The Versatile AI Risk Assessment threat catalogue draws exclusively on 12 primary sources to back its 52 threats. Together they provide 188 verified locations. Every source has its own page here, with the publisher, the version used and the threats that refer to it.
Berryville Institute of Machine Learning (BIML)2 documents
Bundesamt für Sicherheit in der Informationstechnik (BSI)1 document
European Data Protection Board (EDPB)1 document
European Union (EUR-Lex)2 documents
- Regulation (EU) 2024/1689 (Artificial Intelligence Act), as amended by Regulation (EU) 2026/1744; consolidated text OJ L 2024/1689, 12.07.2024, as amended by Regulation (EU) 2026/1744 (OJ L 2026/1744, 24.07.2026); consolidated version 02024R1689-20260727 · 18 locations · 51 threats
- Regulation (EU) 2016/679 (GDPR), authentic Official Journal text OJ L 119, 04.05.2016 · 3 locations · 8 threats
MITRE1 document
National Institute of Standards and Technology (NIST)3 documents
- Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations NIST AI 100-2e2025 · 23 locations · 29 threats
- Artificial Intelligence Risk Management Framework: Generative Artificial Intelligence Profile NIST AI 600-1 · 11 locations · 38 threats
- Artificial Intelligence Risk Management Framework (AI RMF 1.0) NIST AI 100-1 / AI RMF 1.0 · 7 locations · 18 threats
OWASP Foundation2 documents
No matching sources. Try another search term.
This page does not reproduce the text of the standards. It states the identifier, title and location of the clause; the wording itself is in the original document. The mappings are taxonomic and not evidence of compliance.