AI-driven vulnerability discovery / exploit generation
LLMs find flaws and weaponise CVEs into working exploits
categoryAI/ML and emerging attacksseverityHighdetectabilityNonelabnot yet measured
Example: AI-found 2FA-bypass zero-day
Classification
19 values: 7 imported, 1 derived, 11 machine-classified. 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 | Medium |
| Resources required | Medium |
| Likelihood / prevalence | Medium |
| Maturity | Emerging |
Impact & scope
| Severity | High |
|---|---|
| Impact | AvailabilityConfidentialityIntegrity |
| Platform | AI SystemPRE |
| Environment | AI system |
| Target asset class | ML model / agent |
| Kill-chain phase (tactic) | Resource Development |
Detection & telemetry
| Detectability | None |
|---|
Detection & response
Mitigated by 4
- AML.M0001 atlas-mitigation
- AML.M0020 atlas-mitigation
- AML.M0022 atlas-mitigation
- M1056 attack-mitigation
Detected by 1
- DET0894 attack-detection-strategy
Framework references
- Primary source: https://cloud.google.com/blog/topics/threat-intelligence/ai-vulnerability-exploitation-initial-access
- attack: T1587.004 (primary)
- atlas: AML.T0016.002
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 652 of Cyber-Attack-Taxonomy.md
- ev-0002 (Seeded-record enrichment run 2026-09-30 (crosswalk + facet classification)) — Crosswalk to attack:T1587.004, atlas:AML.T0016.002 as the nearest framework entries; ids verified to exist in the cached catalogues.
- ev-0003 (MITRE Enterprise ATT&CK v19.2 (STIX 2.1)) — ATT&CK usage prevalence: 5 groups/software/campaigns reference this technique (ATT&CK enterprise v19.2)