A stochastic neural network defense using randomly switched parallel weight channels achieves a high defense-per-accuracy-drop ratio on MNIST and CIFAR-10 and is reported as the first defense against adversarial reprogramming.
Dhillon, Kamyar Aziz- zadenesheli, Jeremy D
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Protecting Neural Networks with Hierarchical Random Switching: Towards Better Robustness-Accuracy Trade-off for Stochastic Defenses
A stochastic neural network defense using randomly switched parallel weight channels achieves a high defense-per-accuracy-drop ratio on MNIST and CIFAR-10 and is reported as the first defense against adversarial reprogramming.