Train Proxy via Gathered ML Artifacts (a40d6631-9042-4ba2-8a5b-5bd162ffb4bc)
Proxy models may be trained from ML artifacts (such as data, model architectures, and pre-trained models) that are representative of the target model gathered by the adversary. This can be used to develop attacks that require higher levels of access than the adversary has available or as a means to validate pre-existing attacks without interacting with the target model.
| Cluster A | Galaxy A | Cluster B | Galaxy B | Level |
|---|---|---|---|---|
| Create Proxy ML Model (12887d43-f8b6-4191-adab-d1728687f951) | MITRE ATLAS Attack Pattern | Train Proxy via Gathered ML Artifacts (a40d6631-9042-4ba2-8a5b-5bd162ffb4bc) | MITRE ATLAS Attack Pattern | 1 |