MITRE ATLAS · AI Model Access
AML.T0040 · AI Model Inference API Access
Adversaries may gain access to a model via legitimate access to the inference API. Inference API access can be a source of information to the adversary (Discover AI Model Ontology, Discover AI Model Family), a means of staging the attack (Verify Attack, Craft Adversarial Data), or for introducing data to the target system for Impact (Evade AI Model, Erode AI Model Integrity).
Mitigations
- Control Access to AI Models and Data in Production
- AI Telemetry Logging and Monitoring
- AI Honeypots
Detections 6
- Bedrock model-access enablement APIs called with a long-term access key
- Bedrock invocation probing: failed model calls across models or regions
- Bedrock reconnaissance burst: model, availability and logging checks in one hour
- Bedrock invocation volume far above a principal's own baseline
- Vertex AI inference from a principal not seen in the previous two weeks
- Ollama API (port 11434) listening on all interfaces or accepting public connections
In the news
No stories mapped to this technique yet.
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.