Exfiltration via AI Inference API: Infer Training Data Membership AML.T0024.000

Adversaries may infer the membership of a data sample or global characteristics of the data in its training set, which raises privacy concerns. Some strategies make use of a shadow model that could be obtained via Train Proxy via Replication, others use statistics of model prediction scores.

MITRE ATLAS technique. Tactics: Exfiltration. View on atlas.mitre.org