LLM-assisted phishing at scale
AI crafts, localises and personalises lures and org-chart recon
categoryAI/ML and emerging attacksseverityHighlabnot yet measured
Classification
18 values: 10 reviewed, 6 imported, 2 derived. What do these mean?
Exploitability
| Attack vector | AI model manipulation |
|---|---|
| Reach (CVSS) | |
| Attack complexity | Low |
| Privileges required | None |
| User interaction | Active |
| Attacker skill required | Low |
| Resources required | Low |
| Likelihood / prevalence | High |
| Maturity | Emerging |
Impact & scope
| Severity | High |
|---|---|
| Impact | ConfidentialityFinancial |
| Platform | AI System |
| Environment | AI system |
| Target asset class | ML model / agent |
| Kill-chain phase (tactic) | Initial AccessLateral Movement |
Detection & response
Mitigated by 2
Framework references
- Primary source: https://cloud.google.com/blog/topics/threat-intelligence/from-prompting-to-autonomy-the-evolution-of-adversarial-ai/
- atlas: AML.T0052 (primary)
Evidence & sources
- ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 654 of Cyber-Attack-Taxonomy.md