Scan for Exposed AI Infrastructure
Sub-technique of AML.T0006 Active Scanning
Description
Adversaries may scan network ports and services to identify deployed AI backends, model-serving endpoints, and AI agent infrastructure reachable over the internet. Self-hosted AI runtimes typically listen on predictable, well-known ports and expose standard API paths, allowing adversaries to efficiently locate candidate hosts and infer the platform running on them.
After identifying candidate hosts, adversaries can interact with them directly to confirm live AI services, fingerprint the software stack, and determine version and configuration details. This information can be used to select exploitable targets and tailor subsequent access attempts.
- ATLAS ID
- AML.T0006.002
- Maturity
- FeasibleShown to be possible in principle (proof of concept).
- Platforms
- Predictive AIGenerative AIAgentic AIEnterprise
Mitigations
- AML.M0039AI Honeypots
By capturing adversarial fingerprinting behavior, honeypots can help provide early warning of sweeping activity meant to discover exposed AI targets and attack surfaces being explored by adversaries.
Case studies that use it
No ATLAS case study records this technique yet. Browse all case studies.
Related ATT&CK technique
ATLAS adapts this technique from MITRE ATT&CK Enterprise.
Marked techniques are also explained, with detection notes and certification relevance, on our interactive ATT&CK map.