Unsafe ML Artifacts (be6ef5c5-1ecb-486d-9743-42085bd2c256)
Adversaries may develop unsafe ML artifacts that when executed have a deleterious effect. The adversary can use this technique to establish persistent access to systems. These models may be introduced via a ML Supply Chain Compromise.
Serialization of models is a popular technique for model storage, transfer, and loading. However, this format without proper checking presents an opportunity for code execution.
Cluster A | Galaxy A | Cluster B | Galaxy B | Level |
---|---|---|---|---|
User Execution (ATLAS) (8c849dd4-5d15-45aa-b5b2-59c96a3ab939) | MITRE ATLAS Attack Pattern | Unsafe ML Artifacts (be6ef5c5-1ecb-486d-9743-42085bd2c256) | MITRE ATLAS Attack Pattern | 1 |