MISLEADER trains an ensemble of distilled models that stay accurate for benign users but output misleading predictions on augmented inputs, reducing clone model accuracy in model extraction attacks.
Backpropagation and stochastic gradient descent method.Neurocomputing, 5(4-5):185–196, 1993
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models
MISLEADER trains an ensemble of distilled models that stay accurate for benign users but output misleading predictions on augmented inputs, reducing clone model accuracy in model extraction attacks.