Hide Navigation Hide TOC

Model Distribution Methods (432c3a44-3974-4b73-9eb9-fa5dd5298e47)

Deploying ML models to edge devices can increase the attack surface of the system. Consider serving models in the cloud to reduce the level of access the adversary has to the model. Also consider computing features in the cloud to prevent gray-box attacks, where an adversary has access to the model preprocessing methods.

Cluster A	Galaxy A	Cluster B	Galaxy B	Level
Model (452b8fdf-8679-4013-bb38-4d16f65430bc)	MITRE ATLAS Attack Pattern	Model Distribution Methods (432c3a44-3974-4b73-9eb9-fa5dd5298e47)	MITRE ATLAS Course of Action	1
Full ML Model Access (3de90963-bc9f-4ae1-b780-7d05e46eacdd)	MITRE ATLAS Attack Pattern	Model Distribution Methods (432c3a44-3974-4b73-9eb9-fa5dd5298e47)	MITRE ATLAS Course of Action	1
Model Distribution Methods (432c3a44-3974-4b73-9eb9-fa5dd5298e47)	MITRE ATLAS Course of Action	White-Box Optimization (ab01ba21-1438-4cd9-a588-92eb271086bc)	MITRE ATLAS Attack Pattern	1
Model (452b8fdf-8679-4013-bb38-4d16f65430bc)	MITRE ATLAS Attack Pattern	ML Supply Chain Compromise (d2cf31e0-a550-4fe0-8fdb-8941b3ac00d9)	MITRE ATLAS Attack Pattern	2
Craft Adversarial Data (a7c30122-b393-4265-91b7-57cd1211e3f9)	MITRE ATLAS Attack Pattern	White-Box Optimization (ab01ba21-1438-4cd9-a588-92eb271086bc)	MITRE ATLAS Attack Pattern	2