Share Email Print

Proceedings Paper

Understanding information leakage of distributed inference with deep neural networks: overview of information theoretic approach and initial results
Author(s): Tiffany Tuor; Shiqiang Wang; Kin K. Leung; Bong Jun Ko
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

With the emergence of Internet of Things (IoT) and edge computing applications, data is often generated by sensors and end users at the network edge, and decisions are made using these collected data. Edge devices often require cloud services in order to perform intensive inference tasks. Consequently, the inference of deep neural network (DNN) model is often partitioned between the edge and the cloud. In this case, the edge device performs inference up to an intermediate layer of the DNN, and offloads the output features to the cloud for the inference of the remaining of the network. Partitioning a DNN can help to improve energy efficiency but also rises some privacy concerns. The cloud platform can recover part of the raw data using intermediate results of the inference task. Recently, studies have also quantified an information theoretic trade-off between compression and prediction in DNNs. In this paper, we conduct a simple experiment to understand to which extent is it possible to reconstruct the raw data given the output of an intermediate layer, in other words, to which extent do we leak private information when sending the output of an intermediate layer to the cloud. We also present an overview of mutual-information based studies of DNN, to help understand information leakage and some potential ways to make distributed inference more secure.

Paper Details

Date Published: 4 May 2018
PDF: 8 pages
Proc. SPIE 10635, Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR IX, 106350K (4 May 2018); doi: 10.1117/12.2306000
Show Author Affiliations
Tiffany Tuor, Imperial College London (United Kingdom)
Shiqiang Wang, IBM Thomas J. Watson Research Ctr. (United States)
Kin K. Leung, Imperial College London (United Kingdom)
Bong Jun Ko, IBM Thomas J. Watson Research Ctr. (United States)

Published in SPIE Proceedings Vol. 10635:
Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR IX
Michael A. Kolodny; Dietrich M. Wiegmann; Tien Pham, Editor(s)

© SPIE. Terms of Use
Back to Top