 |
 Robustness via curvature regularization, and vice versaComputer Vision and Pattern Recognition (CVPR), 2018 |
 Decoupling Direction and Norm for Efficient Gradient-Based L2
Adversarial Attacks and DefensesComputer Vision and Pattern Recognition (CVPR), 2018 |
 Parametric Noise Injection: Trainable Randomness to Improve Deep Neural
Network Robustness against Adversarial AttackComputer Vision and Pattern Recognition (CVPR), 2018 |
 Recognizing Disguised Faces in the WildIEEE Transactions on Biometrics Behavior and Identity Science (TBBIS), 2018 |
 Generalizable Adversarial Training via Spectral NormalizationInternational Conference on Learning Representations (ICLR), 2018 |
 A Geometric Perspective on the Transferability of Adversarial DirectionsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2018 |
 SparseFool: a few pixels make a big differenceComputer Vision and Pattern Recognition (CVPR), 2018 |
