Generating IoT traffic: A Case Study on Anomaly Detection

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

1 Citation (Scopus)

Abstract

The Internet of Things (IoT) is expected to count for a large part of the Internet traffic and its impact on the network is still widely unknown. It is therefore essential to study the IoT Traffic in order to characterize its properties and evaluate its performances. In this paper, we propose a novel IoT traffic generator called IoTTGen. We model the IoT traffic and we generate synthetic traffic for smart home and bio-medical IoT environments. We also extracted anomalous IoT traffic from a real dataset and study the IoT traffic properties by computing the entropy value of traffic parameters. Our generator succeeds in capturing the characteristics of the IoT traffic, which can be visually observed on Behavior Shape graphs. Our generator can also serve to describe the main IoT traffic properties and also to detect IoT traffic anomalies.

Original languageEnglish
Title of host publication2020 IEEE International Symposium on Local and Metropolitan Area Networks, LANMAN 2020
PublisherIEEE Computer Society
ISBN (Electronic)9781728181547
DOIs
Publication statusPublished - 2020 Jul
Event26th IEEE International Symposium on Local and Metropolitan Area Networks, LANMAN 2020 - Virtual, Online, United States
Duration: 2020 Jul 132020 Jul 15

Publication series

NameIEEE Workshop on Local and Metropolitan Area Networks
Volume2020-July
ISSN (Print)1944-0367
ISSN (Electronic)1944-0375

Conference

Conference26th IEEE International Symposium on Local and Metropolitan Area Networks, LANMAN 2020
CountryUnited States
CityVirtual, Online
Period20/7/1320/7/15

Keywords

  • Anomaly detection
  • Entropy
  • IoT
  • Traffic Analysis
  • Traffic Generator

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Software
  • Electrical and Electronic Engineering
  • Communication

Fingerprint Dive into the research topics of 'Generating IoT traffic: A Case Study on Anomaly Detection'. Together they form a unique fingerprint.

Cite this