ML Anthology

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

Ilia Sucholutsky, Matthias Schonlau
AAAI 2021 pp. 15897-15898
doi:10.1609/AAAI.V35I18.17945 /aaai/2021/sucholutsky2021aaai-secdd/

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.

PDF AAAI Semantic Scholar

Cite

Text

Sucholutsky and Schonlau. "SecDD: Efficient and Secure Method for Remotely Training Neural Networks (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021. doi:10.1609/AAAI.V35I18.17945

Markdown

[Sucholutsky and Schonlau. "SecDD: Efficient and Secure Method for Remotely Training Neural Networks (Student Abstract)." AAAI Conference on Artificial Intelligence, 2021.](https://mlanthology.org/aaai/2021/sucholutsky2021aaai-secdd/) doi:10.1609/AAAI.V35I18.17945

BibTeX

@inproceedings{sucholutsky2021aaai-secdd,
  title     = {{SecDD: Efficient and Secure Method for Remotely Training Neural Networks (Student Abstract)}},
  author    = {Sucholutsky, Ilia and Schonlau, Matthias},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {15897-15898},
  doi       = {10.1609/AAAI.V35I18.17945},
  url       = {https://mlanthology.org/aaai/2021/sucholutsky2021aaai-secdd/}
}