Security of Distributed Intelligence in Edge Computing: Threats and Countermeasures

Mohammad S. Ansari, Saeed H. Alsamhi, Yuansong Qiao, Brian Lee, Yuhang Ye

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

34 Citations (Scopus)

Abstract

Rapid growth in the amount of data produced by IoT sensors and devices has led to the advent of edge computing wherein the data is processed at a point at or near to its origin. This facilitates lower latency, as well as data security and privacy by keeping the data localized to the edge node. However, due to the issues of resource-constrained hardware and software heterogeneities, most edge computing systems are prone to a large variety of attacks. Furthermore, the recent trend of incorporating intelligence in edge computing systems has led to its own security issues such as data and model poisoning, and evasion attacks. This chapter presents a discussion on the most pertinent threats to edge intelligence. Countermeasures to deal with the threats are then discussed. Lastly, avenues for future research are highlighted.

Original languageEnglish
Title of host publicationPalgrave Studies in Digital Business and Enabling Technologies
PublisherPalgrave Macmillan
Pages95-122
Number of pages28
DOIs
Publication statusPublished - 2020

Publication series

NamePalgrave Studies in Digital Business and Enabling Technologies
ISSN (Print)2662-1282
ISSN (Electronic)2662-1290

Keywords

  • Distributed intelligence
  • Edge AI
  • Edge computing
  • Federated learning
  • Threats to Edge AI

Fingerprint

Dive into the research topics of 'Security of Distributed Intelligence in Edge Computing: Threats and Countermeasures'. Together they form a unique fingerprint.

Cite this