Improving Adversarial Robustness Requires Revisiting Misclassified Examples.

Yisen Wang Difan Zou Jinfeng Yi James Bailey Xingjun Ma Quanquan Gu

Published in: ICLR (2020)

Keyphrases

training examples
neural network
real world
high robustness
multiscale
reinforcement learning
search algorithm
feature space
relational databases
hyperplane
correctly classified