Using Local Convolutional Units to Defend Against Adversarial Examples

Matej Kocián, Martin PilátIJCNN 2019 · OpenReview

Abstract

Deep neural networks are known to be sensitive to adversarial examples - inputs that are created in such a way that they are similar (if viewed by people) to clean inputs, but the neural network has high confidence that they belong to another class. In this paper, we study a new type of neural network unit similar to the convolutional units, but with a more local behavior. The unit is based on the Gaussian radial basis function. We show that if we replace the first convolutional layer in a convolutional network by the new layer (called RBFolutional), we obtain better robustness towards adversarial samples on the MNIST and CIFAR10 datasets, without sacrificing the performance on the clean examples.
BibTeX
@inproceedings{kocian2019using,
  author = {Matej Kocián and Martin Pilát},
  title = {{Using Local Convolutional Units to Defend Against Adversarial Examples}},
  booktitle = {IJCNN},
  year = {2019},
  url = {https://openreview.net/forum?id=nf8OaMUKgj},
}

Loading related content...

Figure