SecDD: Efficient and Secure Method for Remotely Training Neural Networks (Student Abstract)

Ilia Sucholutsky, Matthias Schonlau

Abstract

We leverage what are typically considered the worst qualities of deep learning algorithms - high computational cost, requirement for large data, no explainability, high dependence on hyper-parameter choice, overfitting, and vulnerability to adversarial perturbations - in order to create a method for the secure and efficient training of remotely deployed neural networks over unsecure channels.
BibTeX
@inproceedings{sucholutsky2021secdd,
  author = {Ilia Sucholutsky and Matthias Schonlau},
  title = {{SecDD: Efficient and Secure Method for Remotely Training Neural Networks (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2021},
  doi = {10.1609/aaai.v35i18.17945},
}
Figure