Defensive distillation does not meaningfully improve the robustness of text-classification neural networks against adversarial examples or reduce attack transferability.
(ed.): WordNet: An Electronic Lexical Database
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples
Defensive distillation does not meaningfully improve the robustness of text-classification neural networks against adversarial examples or reduce attack transferability.