MT-MTD: Muti-Training based Moving Target Defense Trojaning Attack in Edged-AI network

Yihao Qiu, Jun Wu, Shahid Mumtaz, Jianhua Li, Anwer Al-Dulaimi, Joel J.P.C. Rodrigues

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The evolution of deep learning has promoted the popularization of smart devices. However, due to the insufficient development of computing hardware, the ability to conduct local training on smart devices is greatly restricted, and it is usually necessary to deploy ready-made models. This opacity makes smart devices vulnerable to deep learning backdoor attacks. Some existing countermeasures against backdoor attacks are based on the attacker's ignorance of defense. Once the attacker knows the defense mechanism, he can easily overturn it. In this paper, we propose a Trojaning attack defense framework based on moving target defense(MTD) strategy. According to the analysis of attack-defense game types and confrontation process, the moving target defense model based on signaling game was constructed. The simulation results show that in most cases, our technology can greatly increase the attack cost of the attacker, thereby ensuring the availability of Deep Neural Networks(DNN) and protecting it from Trojaning attacks.

Original languageEnglish
Title of host publicationICC 2021 - IEEE International Conference on Communications, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728171227
DOIs
Publication statusPublished - 2021 Jun
Externally publishedYes
Event2021 IEEE International Conference on Communications, ICC 2021 - Virtual, Online, Canada
Duration: 2021 Jun 142021 Jun 23

Publication series

NameIEEE International Conference on Communications
ISSN (Print)1550-3607

Conference

Conference2021 IEEE International Conference on Communications, ICC 2021
Country/TerritoryCanada
CityVirtual, Online
Period21/6/1421/6/23

Keywords

  • deep neural network
  • Edged-AI
  • moving target defense
  • Trojaning attack

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'MT-MTD: Muti-Training based Moving Target Defense Trojaning Attack in Edged-AI network'. Together they form a unique fingerprint.

Cite this