SecureAEye LAB ONLINE · SIG 657 · DET ~41s

← All attacks / AI/ML and emerging attacks

AI-generated / polymorphic malware

Malware queries an LLM at runtime to rewrite its code

categoryAI/ML and emerging attacksseverityHighdetectabilityNonelabnot yet measured

Example: PROMPTFLUX; BlackMamba PoC

Classification

29 values: 13 imported, 2 derived, 14 machine-classified. What do these mean?

Exploitability

Attack vectorAI model manipulationMalware
Reach (CVSS)Local
Attack complexityHigh
Privileges requiredNone
User interactionActive
Attacker skill requiredMedium
Resources requiredLow
Likelihood / prevalenceLow
MaturityProof of concept

Impact & scope

SeverityHigh
ImpactConfidentialityIntegrity
PlatformLinuxmacOSWindows
EnvironmentAI systemOn-premises
Target asset classEndpoint
Kill-chain phase (tactic)Stealth

Detection & telemetry

DetectabilityNone
Data sources (ATT&CK data components)File CreationFile ModificationModule LoadProcess AccessProcess CreationProcess Modification
Defense bypassedSignature-based detection

Detection & response

Mitigated by 2

Detected by 1

Framework references

Evidence & sources

  • ev-0001 (Cyber Attack Taxonomy) — Name, definition and Example/ID taken verbatim from the 'AI/ML and emerging attacks' table, line 653 of Cyber-Attack-Taxonomy.md
  • ev-0002 (Seeded-record enrichment run 2026-09-30 (crosswalk + facet classification)) — Crosswalk to attack:T1027.014 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: 1 groups/software/campaigns reference this technique (ATT&CK enterprise v19.2)