Edge-assisted CNN inference over encrypted data for internet of things

Yifan Tian, Jiawei Yuan, Shucheng Yu, Yantian Hou, Houbing Song

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Supporting the inference tasks of convolutional neural network (CNN) on resource-constrained Internet of Things (IoT) devices in a timely manner has been an outstanding challenge for emerging smart systems. To mitigate the burden on IoT devices, one prevalent solution is to offload the CNN inference tasks to the public cloud. However, this “offloading-to-cloud” solution may cause privacy breach since the offloaded data can contain sensitive information. For privacy protection, the research community has resorted to advanced cryptographic primitives to support CNN inference over encrypted data. Nevertheless, these attempts are limited by the real-time performance due to the heavy IoT computational overhead brought by cryptographic primitives. In this paper, we propose an edge-computing-assisted scheme to boost the efficiency of CNN inference tasks on IoT devices, which also protects the privacy of IoT data to be offloaded. In our scheme, the most time-consuming convolutional and fully-connected layers are offloaded to edge computing devices and the IoT device only performs efficient encryption and decryption on the fly. As a result, our scheme enables IoT devices to securely offload over 99% CNN operations, and edge devices to execute CNN inference over encrypted data as efficiently as on plaintext. Experiments on AlexNet show that our scheme can speed up CNN inference for more than 35× with a 95.56% energy saving for IoT devices.

Original languageEnglish
Title of host publicationSecurity and Privacy in Communication Networks - 15th EAI International Conference, SecureComm 2019, Proceedings
EditorsSongqing Chen, Kim-Kwang Raymond Choo, Xinwen Fu, Wenjing Lou, Aziz Mohaisen
Pages85-104
Number of pages20
DOIs
StatePublished - 2019
Event15th International Conference on Security and Privacy in Communication Networks, SecureComm 2019 - Orlando , United States
Duration: 23 Oct 201925 Oct 2019

Publication series

NameLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume304 LNICST
ISSN (Print)1867-8211

Conference

Conference15th International Conference on Security and Privacy in Communication Networks, SecureComm 2019
Country/TerritoryUnited States
CityOrlando
Period23/10/1925/10/19

Keywords

  • Convolutional neural network
  • Deep learning
  • Edge computing
  • Internet of Things
  • Privacy

Fingerprint

Dive into the research topics of 'Edge-assisted CNN inference over encrypted data for internet of things'. Together they form a unique fingerprint.

Cite this