Skip to content
CaMLSysUniversity of Cambridge
Home People Publications Projects Contact

← All publications

A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics

  • Seyed Ali OsiaSharif University of Technology
  • Ali Shahin ShamsabadiQueen Mary University of London
  • Sina SajadmaneshIdiap Research Institute
  • Ali TaheriSharif University of Technology
  • Kleomenis KatevasImperial College London
  • Hamid R. RabieeSharif University of Technology
  • Nicholas D. LaneUniversity of Oxford
  • Hamed HaddadiImperial College London

IEEE Internet of Things Journal, 2020

Abstract

Internet of Things (IoT) devices and applications are being deployed in our homes and workplaces. These devices often rely on continuous data collection to feed machine learning models. However, this approach introduces several privacy and efficiency challenges, as the service operator can perform unwanted inferences on the available data. Recently, advances in edge processing have paved the way for more efficient, and private, data processing at the source for simple tasks and lighter models, though they remain a challenge for larger, and more complicated models. In this paper, we present a hybrid approach for breaking down large, complex deep neural networks for cooperative, privacy-preserving analytics. To this end, instead of performing the whole operation on the cloud, we let an IoT device to run the initial layers of the neural network, and then send the output to the cloud to feed the remaining layers and produce the final result. In order to ensure that the user’s device contains no extra information except what is necessary for the main task and preventing any secondary inference on the data, we introduce Siamese fine-tuning. We evaluate the privacy benefits of this approach based on the information exposed to the cloud service. We also assess the local inference cost of different layers on a modern handset. Our evaluations show that by using Siamese fine-tuning and at a small processing cost, we can greatly reduce the level of unnecessary, potentially sensitive information in the personal data, and thus achieving the desired trade-off between utility, privacy, and performance.

Materials

  • PDF
BibTeX
@article{osia2020hybrid,
  title = {{A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics}},
  author = {Osia, Seyed Ali and Shamsabadi, Ali Shahin and Sajadmanesh, Sina and Taheri, Ali and Katevas, Kleomenis and Rabiee, Hamid R. and Lane, Nicholas D. and Haddadi, Hamed},
  year = {2020},
  journal = {IEEE Internet of Things Journal},
  volume = {7},
  number = {5},
  pages = {4505--4518},
  publisher = {IEEE},
  doi = {10.1109/JIOT.2020.2967734}
}
Cambridge Machine Learning Systems Group
Department of Computer Science and Technology
University of Cambridge
ContactGitHub