Model inversion / data reconstruction
Reconstructing training data from model outputs
categoryAI/ML and emerging attacksseverityHighlabnot yet measured
Classification
15 values: 9 reviewed, 5 imported, 1 derived. What do these mean?
Exploitability
| Attack vector | AI model manipulation |
|---|---|
| Reach (CVSS) | Network |
| Attack complexity | High |
| Privileges required | None |
| User interaction | None |
| Attacker skill required | High |
| Resources required | Medium |
| Likelihood / prevalence | Low |
| Maturity | Theoretical |
Impact & scope
| Severity | High |
|---|---|
| Impact | Confidentiality |
| Platform | AI System |
| Environment | AI system |
| Target asset class | ML model / agent |
| Kill-chain phase (tactic) | Exfiltration |
Detection & response
Mitigated by 4
- AML.M0002 atlas-mitigation
- AML.M0004 atlas-mitigation
- AML.M0024 atlas-mitigation
- AML.M0035 atlas-mitigation
Framework references
- Primary source: https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.100-2e2025.pdf
- atlas: AML.T0024.001 (primary)
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 622 of Cyber-Attack-Taxonomy.md