RADEP stacks existing defenses (adversarial training, uncertainty-based query detection, output perturbation, watermarking) to reduce the accuracy of extracted models, with experiments on MNIST, F-MNIST, CIFAR-10, and ImageNette.
A comprehensive defense framework against model extraction attacks,
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
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
RADEP: A Resilient Adaptive Defense Framework Against Model Extraction Attacks
RADEP stacks existing defenses (adversarial training, uncertainty-based query detection, output perturbation, watermarking) to reduce the accuracy of extracted models, with experiments on MNIST, F-MNIST, CIFAR-10, and ImageNette.