PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training with A Fine-Grained Privacy Control

@article{Li2017PrivyNetAF,
  title={PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training with A Fine-Grained Privacy Control},
  author={Meng Li and Liangzhen Lai and Naveen Suda and Vikas Chandra and David Z. Pan},
  journal={CoRR},
  year={2017},
  volume={abs/1709.06161}
}
Massive data exist among user local platforms that usually cannot support deep neural network (DNN) training due to computation and storage resource constraints. Cloud-based training schemes provide beneficial services, but suffer from potential privacy risks due to excessive user data collection. To enable cloud-based DNN training while protecting the data privacy simultaneously, we propose to leverage the intermediate representations of the data, which is achieved by splitting the DNNs and… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-10 of 24 references

The use of multiple measurements in taxonomic problems

  • Ronald A Fisher
  • Annals of human genetics,
  • 1936
Highly Influential
3 Excerpts

Similar Papers

Loading similar papers…