Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness

Konstantinos P. Panousis, Sotirios Chatzis, Sergios TheodoridisZenodo 2021 · DOI · OpenAlex

Abstract

This work explores the potency of stochastic competition-based activations, namely Stochastic Local Winner-Takes-All (LWTA), against powerful (gradient-based) white-box and black-box adversarial attacks; we especially focus on Adversarial Training settings. In our work, we replace the conventional ReLU-based nonlin- earities with blocks comprising locally and stochastically competing linear units. The output of each network layer now yields a sparse output, depending on the outcome of winner sampling in each block. We rely on the Variational Bayesian framework for training and inference; we incorporate conventional PGD-based adversarial training arguments to increase the overall adversarial robustness. As we experimentally show, the arising networks yield state-of-the-art robustness against powerful adversarial attacks while retaining very high classification rate in the benign case.
BibTeX
@inproceedings{panousis2021stochastic,
  author = {Konstantinos P. Panousis and Sotirios Chatzis and Sergios Theodoridis},
  title = {{Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness}},
  booktitle = {Zenodo},
  year = {2021},
  doi = {10.5281/zenodo.6000329},
}

Loading related content...

Figure