Publishing poisoned models / datasets
Trojaned models or datasets uploaded to public hubs
categoryAI/ML and emerging attacksseverityVery Highlabnot yet measured
Classification
17 values: 11 reviewed, 5 imported, 1 derived. What do these mean?
Exploitability
| Attack vector | AI model manipulation |
|---|---|
| Reach (CVSS) | Network |
| Attack complexity | Low |
| Privileges required | None |
| User interaction | Active |
| Attacker skill required | Medium |
| Resources required | Medium |
| Likelihood / prevalence | Medium |
| Maturity | Emerging |
Impact & scope
| Severity | Very High |
|---|---|
| Impact | AvailabilityConfidentialityIntegrity |
| Platform | AI System |
| Environment | AI system |
| Target asset class | ML model / agent |
| Kill-chain phase (tactic) | Resource Development |
Detection & response
Mitigated by 3
Framework references
- Primary source: https://raw.githubusercontent.com/mitre-atlas/atlas-data/main/dist/ATLAS.yaml
- atlas: AML.T0115.001 (primary)
- atlas: AML.T0115.000
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 618 of Cyber-Attack-Taxonomy.md