Showing stat.MLShow all
2 papers · 1 filter
stat.ML2020
Constraining Logits by Bounded Function for Adversarial Robustness
Sekitoshi Kanai, Masanori Yamada, Shin'ya Yamaguchi +2
We propose a method for improving adversarial robustness by addition of a new bounded function just before softmax. Recent studies hypothesize that small logits (inputs of softmax)…
stat.ML2019
Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks
Sekitoshi Kanai, Yasutoshi Ida, Yasuhiro Fujiwara +2
We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, rece…