Imperial College London

DrHamedHaddadi

Faculty of EngineeringDyson School of Design Engineering

Senior Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 2584h.haddadi Website

 
 
//

Location

 

Dyson BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Osia,
author = {Osia, SA and Shamsabadi, AS and Sajadmanesh, S and Taheri, A and Katevas, K and Rabiee, HR and Lane, ND and Haddadi, H},
title = {A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics},
url = {http://arxiv.org/abs/1703.02952v6},
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - Internet of Things (IoT) devices and applications are being deployed in ourhomes and workplaces and in our daily lives. These devices often rely oncontinuous data collection and machine learning models for analytics andactuations. However, this approach introduces a number of privacy andefficiency challenges, as the service operator can perform arbitrary inferenceson the available data. Recently, advances in edge processing have paved the wayfor more efficient, and private, data processing at the source for simple tasksand lighter models, though they remain a challenge for larger, and morecomplicated models. In this paper, we present a hybrid approach for breakingdown large, complex deep neural networks for cooperative, privacy-preservinganalytics. 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 thensend the output to the cloud to feed the remaining layers and produce the finalresult. We manipulate the model with Siamese fine-tuning and propose a noiseaddition mechanism to ensure that the output of the user's device contains noextra information except what is necessary for the main task, preventing anysecondary inference on the data. We then evaluate the privacy benefits of thisapproach based on the information exposed to the cloud service. We also assesthe local inference cost of different layers on a modern handset. Ourevaluations show that by using Siamese fine-tuning and at a small processingcost, we can greatly reduce the level of unnecessary, potentially sensitiveinformation in the personal data, and thus achieving the desired trade-offbetween utility, privacy, and performance.
AU - Osia,SA
AU - Shamsabadi,AS
AU - Sajadmanesh,S
AU - Taheri,A
AU - Katevas,K
AU - Rabiee,HR
AU - Lane,ND
AU - Haddadi,H
TI - A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics
UR - http://arxiv.org/abs/1703.02952v6
ER -