Model Extraction

nounverified·updated May 18, 2026

GlossaryL1 — what DictionaryL2 — how used ThesaurusL3 — relations Universaleverything

Adversaries maliciously exploiting the query interface to steal the model. More precisely, in a model extraction attack, a good approximation of a sensitive or proprietary model held by the server is extracted (i.e. learned) by a dishonest user who interacts with the server only via the query interface.

MWE

Classifications

per-axis with provenance

Entity Type

Threat92%llm-generatedllm:claude-haiku-4-5

?unassignedlast reviewed —

Sensitivity

unclassified

Information Class

unclassified

Variants

5 surface forms

synonym: model inversionmodel stealing
plural: Model Extractions
possessive: Model Extraction's
pluralpossessive: Model Extractions'

Continue to:Dictionary →How is this term used per framework?Thesaurus →How does this term relate to other terms?Universal →Everything in one page.