A hill-climbing search over randomly rotated directions generates adversarial examples with success rates competitive with gradient-based attacks, including in black-box settings.
A unified architecture for natural language processing: Deep neural networks with multitask learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Random Directional Attack for Fooling Deep Neural Networks
A hill-climbing search over randomly rotated directions generates adversarial examples with success rates competitive with gradient-based attacks, including in black-box settings.