Model poisoning
Model parameters manipulated directly, e.g. in federated learning
categoryAI/ML and emerging attacksseverityHighlabnot yet measured
Example: NIST AI 100-2
Classification
16 values: 6 imported, 1 derived, 9 machine-classified. What do these mean?
Exploitability
| Attack vector | AI model manipulation |
|---|---|
| Reach (CVSS) | Network |
| Attack complexity | High |
| Privileges required | Low |
| User interaction | None |
| Attacker skill required | High |
| Resources required | Medium |
| Likelihood / prevalence | Low |
| Maturity | Proof of concept |
Impact & scope
| Severity | High |
|---|---|
| Impact | Integrity |
| Platform | AI System |
| Environment | AI system |
| Target asset class | ML model / agent |
| Kill-chain phase (tactic) | AI Attack StagingPersistence |
Detection & response
Mitigated by 6
- AML.M0005 atlas-mitigation
- AML.M0007 atlas-mitigation
- AML.M0008 atlas-mitigation
- AML.M0013 atlas-mitigation
- AML.M0025 atlas-mitigation
- AML.M0035 atlas-mitigation
Framework references
- Primary source: https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.100-2e2025.pdf
- atlas: AML.T0018.000 (primary)
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 617 of Cyber-Attack-Taxonomy.md
- ev-0002 (Seeded-record enrichment run 2026-09-30 (crosswalk + facet classification)) — Crosswalk to atlas:AML.T0018.000 as the nearest framework entries; ids verified to exist in the cached catalogues.